Common Statistical Densities: Appendix 1

APPENDIX 1
Common Statistical Densities
For convenience, we list here several common statistical densities that are
used in examples and exercises throughout the book. The listings are brief,
giving only the name of the density, the abbreviation that will be used for
the density, the sample space ~, the range of the parameter values, the
density itself, useful moments of the density, important special cases, and
a brief explanation if needed for clarification.
In the listings, det B will stand for the determinant of the matrix B; the
symbol IA(z) is defined by
I A (Z)={1 ifzEA,
o ifzt A,
and is called the indicator function on the set A; and f( a) is the usual
gamma function, defined by
f(a) = LX> e-Xx",-t dx.
We first list the continuous densities, followed by the discrete densities.
I. Continuous
1. Univariate Normal (Jf( IL, (72)): ~ = R t, -00 < IL < 00, (72) 0, and
f(xllL (72) = 1 e-(x- JL )2/ 2 u 2

'(21T)t/2(7 .
Mean = IL, Variance = (72.

560 Appendix 1. Common Statistical Densities
2. p-Variate Normal (.N'p(fI., I»: ~= RP, fI. = (ILI>"" ILp)t E RP, I is a

(p x p) positive definite matrix, and
f( I
X fl.,
I) - 1
- (2'7T V/2( det I )1/2 e
-(x-",)'l;-I(X-",)/2
.
Mean = fl., Covariance matrix = I.
3. Uniform (OU(a, (3»: f£= (a, (3), -00< a <00, a <f3 <00, and
1
f(xla, (3) = f3 _ a I(a,/3)(x).
Mean =!(a + (3), Variance = (f3 - a)2/12.
4. Gamma (C§(a,f3»: f£= (0, (0), a>O, f3>0, and
f(xla, (3) = f(a\f3 a x a - I e- x //3 I(o,oo)(x).
Mean = af3, Variance = af32.
Special Cases:
(a) Exponential ('If(f3)): the C§(1, (3) density.
(b) Chi-square with n degrees offreedom (x 2(n»: the C§(n/2, 2) density.
5. Beta (i?)J£(a,f3»: f£=[0, 1], a>O, f3>0, and
f(
X
Ia, f3 ) -- f(a)f(f3)
f(a+f3) a-I
X
/3-1
(I-x) l(o,i](x).
Mean = a/(a + (3), Variance = af31(a + (3)2(a + f3 + 1).
6. Cauchy (C€(a,f3»: f£=R\ -oo<a<oo, f3>0, and
f(xla, (3) = '7T[f32+~X - a?f

Mean and Variance do not exist.
7. F distribution with a and f3 degrees offreedom (.9f(a, (3»: f£= (0, 00),
a > 0, f3 > 0, and
f[(a + (3)/2]aa/2f3/3/ 2 X a / 2- 1
f(xla,f3)= f(a/2)f(f3I2) . (f3+ax)(a+/3)/2 I(O,OO)(x).
Mean = f3/(f3 -2) if f3 > 2, Variance = 2f32(a + f3 -2)/ a(f3 -4)(f3 _2)2 if
f3 >4.
1. Continuous 561
8. t distribution with a degrees of freedom, location parameter /L, and

scale parameter (72( fJ( a, /L, (72)): 2l' = R I, a > 0, -00 < /L < 00, (72) 0, and
2 f[( a + I)/2] ( (x - /L)2 ) -(a+I)/2

f(xla,/L,(7)= (7(a1T)1/2f(aI2) 1+ a(72
Mean = /L, if a> 1, Variance = a(72/(a - 2) if a> 2.

Note: (X - /L)2 1(72 - ~(1, a).
9. p- Variate t distribution with a degrees of freedom, location vector fl.,

and scale matrix I( fJp ( a, fl., I)): 2l' = R P, a> 0, fl. E R P, I is a (p x p) posi-
tive definite matrix, and
Mean = fl. if a> 1, Covariance matrix = aI/(a -2) if a> 2.

Note: (11p)(X - fl.)'I-I(X - fl.) - ~(p, a).
10. Inverse Gamma (~C§(a,f3)): 2l'=(0, 00), a>O, f3>0, and
f(xla, f3) = f(a)f3:x(a+1) e- l / x /3 I(o,oo)(x).
Mean = II f3(a -1) if a> 1, Variance = II f32(a -I)2(a -2) if a> 2.

Note: II X - C§(a, f3).
11. Dirichlet (f!O(a)):x=(X),,,.,Xk)' where L~=lxj=1 and O:sxj:sl

°
for all i, a = (a), ... , ad' where aj > for all i, and (defining ao = L~=I aj),
I ) --
f( xa k
f(ao) Ok (a.-I)
Xj' .
j
OJ=1 f(a ) j=1
Mean (X;}=aJao, Variance (Xj)=(ao-a;}aJa~(ao+l), Covariance

(Xj , Xj) = -aja) a~( ao + 1).
Note: This is really only a (k -I)-dimensional distribution because of the
restriction on the Xj' In taking expectations with respect to this density,
therefore, replace Xk by 1 - L~:::; Xj and integrate over XI, ... , Xk-l'
12. Pareto (f!Pa,(xo, a)): 2l' = (xo, 00), 0 < Xo < 00, a> 0, and
f(xlxo, a)=: (:or+1I(Xo,OO)(X).
Mean = aXo/(a -1) if a> 1.

562 Appendix 1. Common Statistical Densities
II. Discrete
1. Binomial (OO(n, p»: ~= {O, 1,2, ... , n}, 0:5 P :51, n = 1, 2, ... , and
f(xln, p) = (;) pX(1- p)(n-xl,
where
(;) = (X!)(:!-X)!'
Mean = np, Variance = np( 1 - p).
Here, X is the number of successes in n independent trials when P is the
probability of a success at each individual trial.
2. Poisson (9P(A»: ~={O, 1,2, ... }, A>O, and
Mean = A, Variance = A.
3. Negative Binomial (.KOO(a,p»: ~={O, 1, ... }, 0<p:51, a>O, and
f( I ) =f(x+l)f(a)P
xa,p
f(a+x) a( )"x
I-p .
Mean = a(1- p)/p, Variance = a(1- p)/p2.

When a is an integer, X is the number of failures in a sequence of
independent trials performed until a successes are observed, where p is the
probability of a success at each individual trial.
Special Case: Geometric (~(p»: the .KOO(1,p) density.
4. Multinomial (Al(n, p»: x= (Xlo X2,"" Xk)' where L~=I Xi = nand
each Xi is an integer between 0 and n, p = (PI,"" Pk)' where L~=I Pi = 1
and 0:5 Pi :5 1 for all i, and
n! k x
f(xlp) =nk (.I).n Pi'·
i=1 X,, 1=1
Mean (Xi) = npi> Variance (Xi) = npi(1- Pi), Covariance (Xi> Xj) = -npiPj'
If an independent sample of size n is drawn from a population of k types,
where Pi is the probability that a single observation is of the ith type, then
Xi is the number of individuals of the ith type in the sample.
Note: k = 2 gives the [JJ (n, p) distribution, with P = PI = 1 - P2'
APPENDIX 2
Supplement to Chapter 4
I. Definition and Properties of Hm

The function Hm is defined for v> 0 by
vm / 2
[-mJ! {e
ifm is even,
v
- L -:-
(m/2-1) Vi}
2 i=O II
if m is odd,
m ){ (m-3)/2 V(i+l/2) }
(
r 2+ 1 e [2c1>(J2;;)-1]-
V
i~O f(i+3/2)
where cI> is the standard normal c.d.f. and the summation in the last
expression is defined to be zero when m = 1. Note that
) 2.r;;j;
H 1 (v = {e V [2c1>(J2;;)-I]}
and
V
H2(V) =[ e v -1 ]
A good approximation to Hm , for most purposes, is

l-w
H m (v);;;;;;l 2[(m+6)/1T)]1/2,
-w
where w=2v/(m+2). (This approximation is defined to be
1/{2[(m+6)/1T]1/2} ifw=1.)
564 Appendix 2. Supplement to Chapter 4
Some expressions for Hm in terms of standard special functions are

2v m / 2 e- v
Hm(v) = [my(m/2, v)]'
where y is the incomplete gamma function
y(;,v)= [e-tt(m-2)/2dt;
and
Hm(v) = [evr(; + 1) v- m/ 2Pm(2v) r 1

,
where Pm is the c.d.f. of the chi-square distribution with m degrees of

freedom.
A useful infinite series expansion of Hm is
Hm(v) = [1 + i~dm/2+ 1)(m/2:~) ... (m/2+ i)r 1

,
and a recurrence relation is

2v
H m+i v )=(m+2) Hm(v)-l
(1 )-1 .
II. Development of (4.121) and (4.122)

There are several possible routes to these formulas. The easiest, technically,
is to define P=~Bt(B~Bt)-IB, and write
x = PX + (I - P)X, O=PO+(I -P)O.
Note that PX and (I - P)X are independent, and that (I - P)O is in the null
space of B. Since we are assuming that there is no prior knowledge about
the null space of B (in 8), it is reasonable to choose the constant noninfor-
mative prior for (I - P)O. Furthermore, if we assume "independence" of PO
and (I - P)O a priori, then the independence (conditionally given 0) of PX
and (I - P)X means that the posterior distribution of (I - P)O given X is
simply the posterior given (I - P)X, and the posterior of PO given X is simply
the posterior given PX.
Since (I - P)X is (singular) normal with mean (I - P)O and covariance
matrix (I - P)~(I - p)' = (I - P)~, the posterior for (I - P)8 can be seen to
be (singular) normal with mean (I - P)x and covariance (I - P)~.
To find the posterior mean and covariance matrix for PO given PX, it
suffices to first find the same quantities for BO and BX (and then transform
by H = ~Bt(B~Bt)-I). Now BX - .N'k(BO, B~Bt), and BO has prior mean d
Ill. Verification of Formula (4.123) 565
and covariance matrix C. Imbuing BO with the robust prior 7Tk(BO) (with
p replaced by k, f.1 replaced by d, A replaced by C, and ~ replaced by
B~BI), Lemma 3 (with x then replaced by Bx) yields the posterior mean,
f.11T k(Bx), and covariance matrix, V 1Tk(Bx), for BO. Thus the posterior mean
and covariance matrix for PO = HBO are, respectively,
Hf.11Tk(Bx) and HV 1T k(Bx)W.
Finally, the posterior mean and covariance matrix of 0, with respect to

the implied prior 7T*, are given by
f.11T*(X) = E 1T *(O\x)[O] = E 1T *(O\x)[PO]+ E 1T *(O\x)[(1 - P)O]

= Hf.11T k(Bx) + (I - P)x,
and (using the posterior independence of PO and (I - P)O)
V 1T *(x) = E 1T *(O\x)[(O - f.11T* (x»(O - f.11T* (x) n

= E[(PO - Hf.1 1Tk)(PO - Hf.11Tk)1 + {(I - P)(O -x)}
X{(I-P)(O-xW]
= HV 1Tk(Bx)W + (I - P)~.
Algebra reduces f.11T* and V 1T * to (4.121) and (4.122).
III. Verification of Formula (4.123)

By definition, the posterior distribution of 0 and 0'2, given x and S2, is
(A2.1)
where h is the density of S2 and m(x, S2) is the joint marginal density of
X and S2. Note that
(A2.2)
where 7T;(Olx, 0'2) is the posterior distribution of 0 given x and 0'2, while
m(xI0'2) is the marginal density of x given 0'2.
The approximation that will be made consists of (i) replacing m(xI0'2)
by m(xI8 2 ), where 8 2 = s2/(m +2), and (ii) replacing 7T;(0Ix,0'2) by a
normal distribution (to be denoted!(O» with mean f.1 *(x, S2) and covariance
matrix (0'2/8 2)V*(x, S2). These approximations will be discussed after the
derivation is complete. Using these approximations in (A2.2) and hence
(A2.1), and defining
k( 2) = m(xI8 2)
x, S
m (x,s
2)'
566 Appendix 2. Supplement to Chapter 4
results in the following approximation to 7T;(0, u 2 lx, S2):

?Tp(O, u 2 lx, S2) = k(x, s2)f(0)u- 2h(S2Iu 2).
To make decisions and inferences about 0, the marginal posterior distri-
bution of 0 given x and S2 is needed. This will be given by
?Tp(Olx, S2) = k(x, S2) too f(0)u- 2h(S2Iu2)du2.

For notational convenience in evaluating this integral, let
22. (0, x, S2) = [0 - .... *(x, S2)yV*(X, S2)-1[0 - .... *(x, S2)],
and define k*(x, S2) as k(x, S2) multiplied by all multiplicative constants
and factors (not involving 0 or ( 2 ) from the densities f and h. Then
?Tn(Olx, S2) = k*(x, S2) too u- p exp { - 2: 22.(0, x, S2)} u- m

2
X exp { - 2: 2} u -2 du 2
= k*(x, S2) fOO u-(m+ p+2) exp {_ S22 [1 + 22.(0, x, S2)] }du2.
o 2u m +2
Making the change of variables
22.(0, x, S2)]
z = -S2 [ 1 + .-.:.---:..-..:...--~
2u 2 m +2
results in the expression
A 2 _ * 2 fOO [2(m+ p)/2][z(m+ p-2)/2]e- Z
7Tp (Olx,s )-k (X,s) 0 s(m+ p)[1 +22.(0, x, s2)/(m+2)](m+ p)/2 dz.
Noting that J~ z(m+ p -2)/2 e -z dz = r([m + p]/2), and defining k(x, S2) as
k*(x, S2) multiplied by all new factors not involving 0 above, we finally have
2
I
w
A 2 k(x, s )
7Tp(O x, S ) = [1 + 22.(0, x, s2)/(m + 2)](m+ p)/2'
which is the expression in (4.123).

The rationale behind the approximations (i) and (ii) is that in the
expression
II/2(I + A)-III/2 = (Ip + I -1/2 AI -1/2)-1
= (Ip + I OI/2 AIoI/2/ ( 2)-I,
. replacing u 2 by 0- 2 is a reasonable approximation, in that any resultant

error is like an error in specifying A. We have seen many indications that
the procedures considered are robust against this type of error. The same
type of argument holds for expressions like I(I+A)-I and (X- .... )/(I+
III. Verification of Formula (4.123) 567
A)-l(X - fJ.). It can be seen that all terms in m(x\0'2), fJ.1Tp(X), and V1Tp(x)
are of this type, except for a multiple, I, of V1Tp(x). This multiple cannot
be approximated without significantly altering the distribution, so it is left
as is, introducing the factor 0'2 in the approximation to the covariance
matrix. The replacing of 7T;(9\x, 0'2) by a normal distribution with the same
approximate mean and covariance matrix is the same type of approximation
used to good effect previously.
APPENDIX 3
Technical Arguments from Chapter 7
I. Verification of Formula (7.8)

Letting K'(n) denote the derivative of K(n) (assuming it exists) it is clear
that
= ( - -n2) 1/2 exp { --2(K(n)-8)2

n } K'(n)
27TU 2u
+f
K(n)
-00
1 {n
2u(27Tn)1/2 exP -2u2(y-8)2 dy
}
- f K(n) (
-00
n ) 1/2(y - 8)2)
27TU2
{n 2}
2u2 exp - 2u2 (y - 8) dy.
Integrating by parts shows that
f K(n)
-00 (y - 8)
(-n(Y-8»)
u2
{n }
exp - 2u 2 (y - 8)2 dy
{ n
=(y-8)exp --2(y-8)2
}IK(n) fK(n)
-
{n
exp --2(y-8)2 dy
}
2u 2u
f
-00 -00
{ n
=(K(n)-8)exp --2(K(n)-8)2 - } K(n) {n }
exp --2(y-8)2 dy.
2u -00 2u
II. Verification of Formula (7.10) 569
Hence
d PeeXn < K(n» = ( - -n2) 1/2 exp { - - n2 (K(n) - 0)2 } K'(n)
-d
n 27T(1" 2(1"
+ f
-00
K(n) 1 {n
2(1"(27Tn)I/2 ex P -2(1"2(y-O)2 dy
}
+ 2(1" (1
27Tn
)1/2 [(K(n) - o)exp { - - ; (K(n) -
2(1"
O)2}
- f
-00
K(n) {n }]
exp - 2(1"2 (y - 0)2 dy
= (27Tn(1"2) -1/2 exp { - 2: 2 (K (n) - O)2}
x[nK'(n)+HK(n)- 0)].
Assuming that differentiation under the integral sign is valid in (7.7), it
follows from the above result that
~ r( 7T, 8~) = L. L( 0, ao)(27Tn(1"2)-1/2 exp { - 2:2 (K(n) - O)2}
x[nK'(n) +HK(n) - O)]dP1T( 0)
- J~
r L(O, al)(27Tn(1"2)-1/2 exp {--;
2(1"
(K(n) - O?}
X[nK'(n) +!(K(n) - 8)]dP1T( 0).

Formula (7.8) follows from this and (7.6).
II. Verification of Formula (7.10)

It is first necessary to determine K(n). Recall that 7T n(8Ixn) is a
.N(ILn(Xn),Pn) density (see (7.3)). Note also, from the definitions of the
posterior density and the marginal density, that
2 (1"2 )-1/2
(~ { n }
exp -2(1"2(K(n)-O? 7T(O)=/(K(n)IO)7T(O)
= mn(K(n))7T n(OIK(n)). (A3.1)
Using this in (7.6) and eliminating common constants gives
f oo W(IO - 80 Dexp { _ _
1 [0 - ILn(K(n))f} dO
f8
eo 2Pn
(A3.2)
= 0
-00
W(IO - Ool)exp { __1_ [0 - ILn(K (n
2Pn
))]2} dO.
570 Appendix 3. Technical Arguments from Chapter 7
From the symmetry of the situation, it is clear that equality is achieved in

(A3.2) when
(A3.3)
or (using (7.3» when
2
K(n) = ( 1 +-2
( ) u 2 J.L.
(JO--2 (A3.4)
n1' n1'
Using (A3.1) and (A3.3) in (7.8), and choosing K* = (Jo, gives
(n)) [f
ddn r(1T,5:)= mn(K 90
-t:
2 W(I(J-(Jol)((J-(Jo)1T n((JIK(n»d(J
n- oo
W(I(J-(Jol)((J-(Jo)1T n((JIK(n»d(J ]
= mn(~(n» [f:: W(I(J - (Jo!) «(J - (Jo)(21TPn)-1/2
X exp {- _1_ ( (J - (Jo?} d(J

2Pn
- foo W(I (J - (Jol)( (J - (Jo)(21TPJ -1/2

90
xex p { - 2:n «(J- (Jo)2} d(J J.

A change of variables (y = «(J - (Jo) p~I/2) establishes that
d r( 1T, 5:) = -n-Imn(K(n»

dn foo W(p!(2y)p!,12y(21T)-1/2e-y2/2 dy.
0
(A3.5)
Recalling that
U2 ) ] -1/2
mn(K(n))= [ 21T ( 1'2+-;;-
{I
exp -2(1' 2+u2/n)(K(n)-J.L)2,
}
r ::2r
and noting from (A3.4) that
[K (n) - J.L f = [ ( 1 + ::2) ::2

(Jo - J.L - J.L = ( 1+ «(Jo - J.L)2,
a little algebra shows that (A3.5) is equivalent to (7.10).

Bibliography
Aitchison, J., and Dunsmore, I. R., 1975. Statistical Prediction Analysis. Cambridge
University Press, Cambridge.
Akaike, H., 1978. A new look at the Bayes procedure. Biometrika 65, 53-59.
Alam, K., and Hawkes, J. S., 1979. Minimax property of Stein's estimator. Commun.
Statist.-Theory and Methods A8, 581-590.
Albert, J. H., 1981. Simultaneous estimation of Poisson means. J. Multivariate Anal.
11,400-417.
Albert, J. H., 1983. A gamma-minimax approach for estimating a binomial probabil-
ity. Technical Report, Department of Mathematics and Statistics, Bowling Green
State University, Bowling Green, Ohio.
Albert, J. H., 1984a. Empirical Bayes estimation of a set of binomial probabilities.
J. Statist. Comput. Simul. 20, 129-144.
Albert, J. H., 1984b. Estimation of a normal mean using mixtures of normal priors.
Technical Report, Department of Mathematics and Statistics, Bowling Green
State University, Bowling Green, Ohio.
Albert, J. H., and Gupta, A. K., 1982. Mixtures of Dirichlet distributions and
estimation in contingency tables. Ann. Statist. 10, 1261-1268.
Allais, M., and Hagen, 0.,1979. Expected Utility Hypotheses and the Allais Paradox.
Reidel, Dordrecht.
Alpert, M., and Raifia, H., 1982. A progress report on the training of probability
assessors. In Judgement Under Uncertainty: Heuristics and Biases, D. Kahneman,
P. Slovic, and A. Tversky (Eds.). Cambridge University Press, Cambridge.
Alvo, M., 1977. Bayesian sequential estimates. Ann. Statist. 5, 955-968.
Amster, S. J., 1963. A modified Bayes stopping rule. Ann. Math. Statist. 34, 1404-
1413.
Anscombe, F. J., 1963a. Sequential medical trials. J. Amer. Statist. Assoc. 58, 365-383.
Anscombe, F. J., 1963b. Bayesian inference concerning many parameters with
reference to supersaturated designs. Bull. Int. Statist. Inst. 40, 721-733.
Antoniak, C. E., 1974. Mixtures of Dirichlet processes with applications to Bayesian
nonparametric problems. Ann. Statist. 2, 1152-1174.
Armitage, P., 1961. Contribution to the discussion of C. A. B. Smith, "Consistency
in statistical inference and decision." 1. Roy. Statist. Soc. (Ser. B) 23, 1-37.
572 Bibliography
Arnold, S. F., 1981. The Theory of Linear Models and Multivariate Analysis. Wiley,
New York.
Arrow, K. J., 1966. Social Choice and Individual Values (2nd edn.). Wiley, New York.
Arrow, K. J., Blackwell, D., and Girshick, M. A., 1949. Bayes and minimax solutions
of sequential decision problems. Econometrika 17, 213-244.
Atchison, T. A., and Martz, H. F. (Eds.), 1969. Proceedings of the Symposium on
Empirical Bayes Estimation and Computing in Statistics. Mathematics Series No.
6, Texas Technical University, Lubbock.
Bacharach, M., 1975. Group decisions in the face of differences of opinion. Manage.
Sci. 22, 182-191.
Bahadur, R. R., 1954. Sufficiency and statistical decision functions. Ann. Math.
Statist. 25, 423-462.
Bahadur, R. R., 1958. A note on the fundamental identity of sequential analysis.
Ann. Math. Statist. 29, 534-543.
Balder, E. J., 1980. An extension of the usual model in statistical decision theory
with applications to stochastic optimization problems. 1. Multivariate Anal. 10,
385-397.
Balder, E. J., 1983. Mathematical foundations of statistical decision theory. Preprint
No. 199, Mathematical Institute, University of Utrecht, The Netherlands.
Balder, E. J., 1984. A general approach to lower semicontinuity and lower closure
in optimal control theory. SIAM 1. Control and Optimization 22, 570-598.
Balder, E. J., Gilliland, D. C., and van Houwelingen, J. c., 1983. On the essential
completeness of Bayes empirical Bayes decision rules. Statistics and Decisions
1,503-509.
Baranchik, A. J., 1970. A family of minimax estimators of the mean of a multivariate
normal distribution. Ann. Math. Statist. 41, 642-645.
Barlow, R. E., Mensing, R. W., and Smiriga, N. G., 1984. Combination of expert's
opinions based on decision theory. In Proceedings of the International Conference
on Reliability and Quality Control, A. Basu (Ed.).
Barlow, R. E., and Shor, S. W. W., 1984. Informative stopping rules. Report ORC
84-1, Operations Research Center, University of California, Berkeley.
Barnard, G. A., 1947. A review of "Sequential Analysis" by Abraham Waldo 1. Amer.
Statist. Assoc. 42, 658-669.
Barnard, G. A., 1949. Statistical inference (with discussion). 1. Roy. Statist. Soc.
(Ser. B) 11, 115-139.
Barnard, G. A., 1962. Comments on Stein's "A remark on the likelihood principle."
1. Roy. Statist. Soc. (Ser. A) 125, 569-573.
Barnard, G. A., 1967. The use of the likelihood function in statistical practice.
In Proc. Fifth Berkeley Symp. Math. Statist. Probab. 1, 27-40, University of
California Press, Berkeley.
Barnard, G. A., 1980. Pivotal inference and the Bayesian controversy. In Bayesian
Statistics, J. M. Bernardo, M. H. DeGroot, D. V. Lindley, and A. F. M. Smith
(Eds.). University Press, Valencia.
Barnard, G. A., Jenkins, G. M., and Winsten, C. B., 1962. Likelihood inference and
time series. 1. Roy. Statist. Soc. (Ser. A) 125, 321-372.
Barndorff-Nielsen, 0., 1971. On Conditional Statistical Inference. Matematisk
Institute, Aarhus University, Aarhus.
Barndorff-Nielsen, 0., 1978. Information and Exponential Families in Statistical
Theory. Wiley, New York.
Barnett, V., 1973. Comparative Statistical Inference (2nd edn., 1982). Wiley, New
York.
Bartholomew, D. J., 1967. Hypothesis testing when the sample size is treated as a
random variable. 1. Roy. Statist. Soc. 29, 53-82.
Bibliography 573
Basu, D., 1975. Statistical information and likelihood (with discussion). Sankhyii
(Ser. A) 37,1-71.
Bayes, T., 1783. An essay towards solving a problem in the doctrine of chances.
Phil. Trans. Roy. Soc. 53, 370-418.
Bechhofer, R. E., Kiefer, 1., and Sobel, M., 1968. Sequential Identification and
Ranking Procedures. University of Chicago Press, Chicago.
Becker, G. M., DeGroot, M. H., and Marschak, 1., 1964. Measuring utility by a
single-response sequential method. Behav. Sci. 9, 226-232.
Berger, 1., 1975. Minimax estimation of location vectors for a wide class of densities.
Ann. Statist. 3, 1318-1328.
Berger, 1., 1976a. Admissibility results for generalized Bayes estimators of coordin-
ates of a location vector. Ann. Statist. 4, 334-356.
Berger, 1., 1976b. Minimax estimation of a multivariate normal mean under arbitrary
quadratic loss. J. Multivariate Anal. 6, 256-264.
Berger, 1., 1976c. Admissible minimax estimation of a multivariate normal mean
with arbitrary quadratic loss. Ann. Statist. 4, 223-226.
Berger, 1., 1976d. Inadmissibility results for generalized Bayes estimators of coordin-
ates of a location vector. Ann. Statist. 4, 302-333.
Berger, 1., 1979. Multivariate estimation with nonsymmetric loss functions. In
Optimizing Methods in Statistics, 1. S. Rustagi (Ed.). Academic Press, New
York.
Berger, 1., 1980a. Improving on inadmissible estimators in continuous exponential
families with applications to simultaneous estimation of gamma scale
parameters. Ann. Statist. 8, 545-571.
Berger, 1., 1980b. A robust generalized Bayes estimator and confidence region for
a multivariate normal mean. Ann. Statist. 8, 716-761.
Berger, 1., 1980c. A modification of Brown's technique for proving inadmissibility.
In Recent Developments in Statistical Inference and Data Analysis, K. Matusita
(Ed.). North-Holland, Amsterdam.
Berger, 1., 1982a. Selecting a minimax estimator of a multivariate normal mean.
Ann. Statist. 10, 81-92.
Berger, 1., 1982b. Bayesian robustness and the Stein effect. J. Amer. Statist. Assoc.
77. 358-368.
Berger, J., 1982c. Estimation in continuous expc:lential families: Bayesian estimation
subject to risk restrictions and inadmissibility results. In Statistical Decision
Theory and Related Topics III, S. S. Gupta and J. Berger (Eds.). Academic
Press, New York.
Berger, 1., 1984a. The robust Bayesian viewpoint (with discussion). In Robustness
of Bayesian Analysis, 1. Kadane (Ed.). North-Holland, Amsterdam.
Berger, 1., 1984b. The frequentist viewpoint and conditioning. In Proceedings of the
Berkeley Conference in Honor of Kiefer and Neyman, L. LeCam and R. Olshen
(Eds.). Wadsworth, Belmont.
Berger, 1., 1984c. A review of 1. Kiefer's work on conditional frequentist statistics.
To appear in The Collected Works of Jack Kiefer, L. Brown, I. Olkin, J. Sacks,
and H. Wynn (Eds.). Springer-Verlag, New York.
Berger, 1., 1984d. In defence of the likelihood principle: axiomatics and coherency.
To appear in Bayesian Statistics II, 1. M. Bernardo, M. H. DeGroot, D. Lindley,
and A. Smith (Eds.). North-Holland, Amsterdam.
Berger, 1., 1984e. Bayesian salesmanship. In Bayesian Inference and Decision
Techniques with Applications: Essays in Honor of B. deFinetti, P. K. Goel
and A. Zellner (Eds.). North-Holland, Amsterdam.
574 Bibliography
Berger, J., and Berliner, L. M., 1986. Robust Bayes and empirical Bayes analysis
with e-contaminated priors. Ann. Statist. 14,461-486.
Berger, J., and Berliner, L. M., 1984. Bayesian input in Stein estimation and a new
minimax empirical Bayes estimator. 1. Econometrics 25, 87-108.
Berger, J., Berliner, L. M., and Zaman, A., 1982. General admissibility and inadmissi-
bility results for estimation in a control problem. Ann. Statist. 10, 838-856.
Berger, J., Bock, M. E., Brown, L. D., Casella, G., and Gieser, L., 1977. Minimax
estimation of a normal mean vector for arbitrary quadratic loss and unknown
covariance matrix. Ann. Statist. 5, 763-771.
Berger, J., and Dey, D. K., 1983. Combining coordinates in simultaneous estimation
of normal means. 1. Statist. Planning and Inference 8, 143-160.
Berger, J., and Dey, D. K., 1985. Truncation of shrinkage estimators of normal
means in the nonsymmetric case. In Multivariate Analysis VI, P. R. Krishnaiah
Berger, J., and Haff, L. R., 1983. A class of minimax estimators of a normal mean
vector for arbitrary quadratic loss and unknown covariance matrix. Statistics
and Decisions I, 105-129.
Berger, J., and Sellke, T., 1987. Testing of a point null hypothesis: the irreconcilability
of significance levels and evidence. J. Amer. Statist. Assoc. 82, 112-139.
Berger, J., and Srinivasan, c., 1978. Generalized Bayes estimators in multivariate
problems. Ann. Statist. 6, 783-801.
Berger, J., and Wolpert, R., 1983. Estimating the mean function of a Gaussian
process and the Stein effect. 1 Multivariate Anal. 13, 401-424.
Berger, J., and Wolpert, R., 1984. The Likelihood Principle. Institute of Mathematical
Statistics Monograph Series, Hayward, California.
Berger, R., 1979. Gamma minimax robustness of Bayes rules. Commun. Statist. 8,
543-560.
Berger, R., 1981. A necessary and sufficient condition for reaching a consensus using
DeGroot's method. 1. Amer. Statist. Assoc. 76, 415-418.
Berk, R. H., Brown, L. D., and Cohen, A., 1981. Properties of Bayes sequential
tests. Ann. Statist. 9, 678-682.
Berkson, J., 1938. Some difficulties of interpretation encountered in the application
of the chi-square test. J. Amer. Statist. Assoc. 33, 526-542.
Berliner, L. M., 1983. Improving on inadmissible estimators in the control problem.
Ann. Statist. 11,814-826.
Berliner, L. M., 1984a. Robust Bayesian analysis with applications in reliability.
Technical Report, Department of Statistics, Ohio State University, Columbus.
Berliner, L. M., 1984b. A decision-theoretic structure for robust Bayesian analysis
with applications to the estimation of a multivariate normal mean. In Bayesian
Statistics II, J. M. Bernardo, M. H. DeGroot, D. V. Lindley, and A. F. M. Smith
(Eds.). North-Holland, Amsterdam.
Bernardo, J. M., 1979a. Expected information as expected utility. Ann. Statist. 7,
686-690.
Bernardo, J. M., 1979b. Reference posterior distributions for Bayesian inference
(with discussion). 1 Roy. Statist. Soc. 41, 113-147.
Bernardo, J. M., and Bermudez, J. D., 1984. The choice of variables in probabilistic
classification. In Bayesian Statistics II, J. M. Bernardo, M. H. DeGroot, D. V.
Lindley, and A. F. M. Smith (Eds.). North-Holland, Amsterdam.
Berry, D., 1982. Optimal stopping regions with islands and peninsulas. Ann. Statist.
10, 634-636.
Bibliography 575
Berry, D., and Christensen, R., 1979. Empirical Bayes estimation of a binomial
parameter via mixture of Dirichlet processes. Ann. Statist. 7, 558-568.
Berry, D., and Fristedt, B., 1985. Bandit Problems: Sequential Allocation of
Experiments. Chapman & Hall, London.
Bhattacharya, P. K., 1966. Estimating the mean of a multivariate normal population
with general quadratic loss function. Ann. Math. Statist. 37, 1819-1824.
Bibby, J., and Toutenburg, H., 1977. Prediction and Improved Estimation in Linear
Models. Wiley, New York.
Bickel, P. J., 1981. Minimax estimation of the mean of a normal distribution when
the parameter space is restricted. Ann. Statist. 9, 1301-1309.
Bickel, P. J., 1984. Parametric robustness or small biases can be worthwhile. Ann.
Statist. 12, 864-879.
Bickel, P. J., and Yahav, J. A., 1967. Asymptotically pointwise optimal procedures
in sequential analysis. In Proc. Fifth Berkeley Symp. Math. Statist. Probab. 1,
401-413. University of California Press, Berkeley.
Birnbaum, A., 1955. Characterizations of complete classes of tests of some multipara-
metric hypotheses, with applications to likelihood ratio tests. Ann. Math. Statist.
26,21-36.
Birnbaum, A., 1962. On the foundations of statistical inference (with discussion).
1. Amer. Statist. Assoc. 57, 269-326.
Birnbaum, A., 1977. The Neyman-Pearson theory as decision theory and as inference
theory: with a criticism of the Lindley-Savage argument for Bayesian theory.
Synthese 36, 19-49.
Bishop, Y., Fienberg, S., and Holland, P., 1975. Discrete Multivariate Analysis:
Theory and Practice. MIT Press, Cambridge, Massachusetts.
Blackwell, D., 1951. On the translation parameter problem for discrete variables.
Ann. Math. Statist. 18, 105-11 O.
Blackwell, D., and Girshick, M. A., 1954. Theory of Games and Statistical Decisions.
Wiley, New York. .
Blum, J. R., and Rosenblatt, J., 1967. On partial a priori information in statistical
inference. Ann. Math. Statist. 38, 1671-1678.
Blyth, C. R., 1951. On minimax statistical decision procedures and their admissibility.
Bock, M. E., 1975. Minimax estimators of the mean of a multivariate normal
distribution. Ann. Statist. 3, 209-218.
Bock, M. E., 1982. Employing vague inequality information in the estimation of
normal mean vectors (estimators that shrink to closed convex polyhedra). In
Statistical Decision Theory and Related Topics III, S. S. Gupta and J. Berger
(Eds.). Academic Press, New York.
Bondar, J. Y., 1977. On a conditional confidence property. Ann. Statist. 5, 881-
891.
Bondar, J. Y., and Milnes, P., 1981. Amenability: a survey for statistical applications
of Hunt-Stein and related conditions on groups. Z. Wahrsch. verw. Gebiete 57,
103-128.
Bordley, R. F., 1982. A multiplicative formula for aggregating probability assess-
ments. Manage. Sci. 28, 1137-1148.
Borel, E., 1921. La theorie du jeu et les equations integrales a noyau symetrique.
C. R. Acad. Sci. Paris 173, 1304-1308.
Box, G. E. P., 1980. Sampling and Bayes inference in scientific modelling and
robustness (with discussion). 1. Roy. Statist. Soc. (Ser. A) 143, 383-430.
Box, G. E. P., and Tiao, G. c., 1973. Bayesian Inference in Statistical Analysis.
Addison-Wesley, Reading, Massachusetts.
Brandwein, A., and Strawderman, W., 1980. Minimax estimators of location
parameters for spherically symmetric distributions with concave loss. Ann.
Statist. 8, 279-284.
576 Bibliography
Brier, G. W., 1950. Verification of forecasts expressed in terms of probabilities.

Month. Weather Rev. 78, 1-3.
Brockett, P. L., Charnes, A., and Paick, K. H., 1984. A method for constructing
a unimodal inferential or prior distribution. Working Paper 83/84-2-26,
Department of Finance, University of Texas, Austin.
Brown, L. D., 1966. On the admissibility of invariant estimators of one or more
location parameters. Ann. Math. Statist. 37, 1087-1136.
Brown, L. D., 1971. Admissible estimators, recurrent diffusions, and insoluble
boundary-value problems. Ann. Math. Statist. 42, 855-903.
Brown, L. D., 1973. Estimation with incompletely specified loss functions. 1. Amer.
Brown, L. D., 1976. Notes on Statistical Decision Theory. (Unpublished lecture notes,
Ithaca.)
Brown, L. D., 1977. Closure theorems for sequential-design processes. In Statistical
Decision Theory and Related Topics II, S. S. Gupta and D. S. Moore (Eds.).
Academic Press, New York.
Brown, L. D., 1978. A contribution to Kiefer's theory of conditional confidence
procedures. Ann. Statist. 6, 59-71.
Brown, L. D., 1979. An heuristic method for determining admissibility of estimators-
with applications. Ann. Statist. 7, 960-994.
Brown, L. D., 1980a. A necessary condition for admissibility. Ann. Statist. 8,540-544.
Brown, L. D., 1980b. Examples of Berger's phenomenon in the estimation of
independent normal means. Ann. Statist. 8, 572-585.
Brown, L. D., 1981. A complete class theorem for statistical problems with finite
sample spaces. Ann. Statist. 9, 1289-1300. -
Brown, L. D., 1988. Admissibility in discrete and continuous invariant nonparametric
estimation problems, and in their multinomial analogues. Ann. Statist. 16,
1567-1593.
Brown, L. D., 1985. Foundations of Exponential Families. Institute of Mathematical
Statistics Monograph Series, Hayward. California.
Brown, L. D., Cohen, A., and Samuel-Cahn, E., 1983. A sharp necessary condition
for admissibility of sequential tests-necessary and sufficient conditions for
admissibility of SPRTs. Ann. Statist. 11, 640-653.
Brown, L. D., Cohen, A., and Strawderman, W. E., 1976. A complete class theorem
for strict monotone likelihood ratio with applications. Ann. Statist. 4, 712-722.
Brown, L. D., Cohen, A., and Strawderman, W. E., 1979. Monotonicity of Bayes
sequential tests. Ann. Statist. 7, 1222-1230.
Brown, L. D., Cohen, A., and Strawderman, W. E., 1980. Complete classes for
sequential tests of hypotheses. Ann. Statist. 8, 377-398.
Brown, L. D., and Farrell, R. H., 1985a. Complete class theorems for estimation of
multivariate Poisson means and related problems. Ann. Statist. 13.
Brown, L. D., and Farrell, R. H., 1985b. All admissible linear estimators of a
multivariate Poisson mean. Ann. Statist. 13,282-294.
Brown, L. D., and Fox, M., 1974a. Admissibility of procedures in two-dimensional
location parameter problems. Ann. Statist. 2, 248-266.
Brown, L. D., and Fox, M., 1974b. Admissibility in statistical problems involving a
location or scale parameter. Ann. Statist. 4, 807-814.
Brown, L. D., and Hwang, J. T., 1982. A unified admissibility proof. In Statistical
Decision Theory and Related Topics III, S. S. Gupta and J. Berger (Eds.).
Brown, L. D., and Purves, R., 1973. Measurable selections of extrema. Ann. Statist.
1,902-912.
Brown, P. J., and Zidek, J. V., 1980. Adaptive multivariate ridge regression. Ann.
Statist. 8, 64-74.
Bibliography 577
Buehler, R. J., 1959. Some validity criteria for statistical inference. Ann. Math. Statist.
30, 845-863.
Buehler, R. J., 1971. Measuring information and uncertainty. In Foundations of
Statistical Inference, V. P. Godambe and D. A. Sprott (Eds.). Holt, Rinehart,
and Winston, Toronto.
Buehler, R. J. 1976. Coherent preferences. Ann. Statist. 4, 1051-1064.
Bunke, 0., 1977. Mixed model, empirical Bayes, and Stein estimators. Math. O.F.
Statist. Ser. Statist. 1, 55-68.
Caridi, F., 1983. Characterization of limits of Bayes procedures. J. Multivariate Anal.
13,52-66.
Casella, G., 1980. Minimax ridge regression estimation. Ann. Statist. 8, 1036-1056.
Casella, G., and Hwang, J. T., 1983. Empirical Bayes confidence sets for the mean
of a multivariate normal distribution. 1. Amer. Statist. Assoc. 78, 688-698.
Casella, G., and Strawderman, W., 1981. Estimating a bounded normal mean. Ann.
Statist. 9, 868-876.
Chaloner, K., 1984. Optimal Bayesian experimental design for linear models. Ann.
Statist. 4, 283-300.
Chen, C. F., 1979. Bayesian inference for a normal dispersion matrix and its
applications to stochastic mUltiple regression analysis. 1. Roy. Statist. Soc. (Ser.
B) 41, 235-248.
Chen, S. Y., 1983. Restricted risk Bayes estimation. Ph.D. Thesis, Purdue University,
West Lafayette.
Cheng, P., 1964. Minimax estimates of parameters of distributions belonging to the
exponential family. Chinese Math. Acta. S, 277-299.
Cheng, P., 1982. Admissibility of simultaneous estimation of several parameters. J.
Syst. Sci. Math. Sci. 2, 176-195.
Chernoff, H., 1959. Sequential design of experiments. Ann. Math. Statist. 30, 755-770.
Chernoff, H., 1968. Optimal stochastic control. Sankhyii (Ser. A) 30, 221-252.
Chernoff, H., 1972. Sequential Analysis and Optimal Design. SIAM, Philadelphia.
Chernoff H., and Moses, L. E., 1959. Elementary Decision Theory. Wiley, New
York.
Chou, J. P., 1984. Multivariate exponential families: an identity and the admissibility
of standard estimates. Ph.D. Thesis, Department of Mathematics, University
of California, Los Angeles.
Chow, Y. S., Robbins, H., and Siegmund, D., 1971. Great Expectations: The Theory
of Optimal Stopping. Houghton-Mifflin, Boston.
Chuang, D. T., 1984. Further theory of stable decisions. In Robustness of Bayesian
Analyses, J. Kadane (Ed.). North-Holland, Amsterdam.
Clevenson, M., and Zidek, J., 1975. Simultaneous estimation of the mean of
independent Poisson laws. 1. Amer. Statist. Assoc. 70, 698-705.
Cohen, A., 1966. All admissible estimators of the mean vector. Ann. Math. Statist.
37, 458-470.
Cohen, A., and Sackrowitz, H. D., 1984. Decision theory results for vector risks
with applications. Statistics and Decisions Supplement No.1: Recent Results in
Estimation Theory and Related Topics, 159-176. Oldenbourg, Munich.
Coleman, A., 1982. Game Theory and Experimental Games: The Study of Strategic
Interaction. Pergamon Press, New York.
Copas,1. B., 1969. Compound decisions and empirical Bayes (with discussion). 1.
Roy. Statist. Soc. (Ser. B) 31, 397-425.
Cornfield, J., 1969. The Bayesian outlook and its applications. Biometrics 25, 617 -657.
Cox, D. R., 1958. Some problems connected with statistical inference. Ann. Math.
Statist. 29, 357-372.
Cox, D. R., and Hinkley, D. V., 1974. Theoretical Statistics. Chapman & Hall, London.
Cressie, N., 1982. A useful empirical Bayes identity. Ann. Statist. 10,625-629.
578 Bibliography
Dalal, S. R., and Hall, W. J., 1983. Approximating priors by mixtures of natural
conjugate priors. J. Roy. Statist. Soc. (Ser. B) 45, 278-286.
Das Gupta, A., 1984. Simultaneous estimation of arbitrary scale-parameter prob-
lems under arbitrary quadratic loss. Technical Report # 84-32, Department of
Statistics, Purdue University, West Lafayette.
Das Gupta, A., 1986. Simultaneous estimation in the multiparameter gamma
distribution under weighted quadratic losses. Ann. Statist. 14, 206-219.
Das Gupta, A., and Sinha, B. K., f980. On the admissibility of polynomial estimators
in the one-parameter exponential family. Sankhya (Ser. B) 42, 129-142.
Dawid, A. P., 1973. Posterior expectations for large observations. Biometrika 60,
664-666.
Dawid, A. P., 1982. Intersubjective statistical models. In Exchangeability in Probabil-
ity and Statistics, G. Koch and F. Spizzichino (Eds.). North-Holland,
Amsterdam.
Dawid, A. P., Stone, M., and Zidek, J. V., 1973. Marginalization paradoxes in
Bayesian and structural inference (with discussion). J. Roy. Statist. Soc. (Ser.
B) 35, 189-233.
Deely, J. J., and Lindley, D. V., 1981. Bayes empirical Bayes. J. Amer. Statist. Assoc.
76, 833-841.
de Finetti, B., 1937. Foresight: Its logical laws, its subjective sources. Translated
and reprinted in Studies in Subjective Probability, H. Kyburg and H. Smokier
(Eds.), 1964,93-158. Wiley, New York.
de Finetti, B., 1962. Does it make sense to speak of "Good probability appraisers"?
In The Scientist Speculates, I. J. Good (Ed.). Basic Books, New York.
de Finetti, B., 1972. Probability, Induction, and Statistics. Wiley, New York.
de Finetti, B., 1974, 1975. Theory of Probability, Vols. 1 and 2. Wiley, New York.
DeGroot, M. H., 1970. Optimal Statistical Decisions. McGraw-Hill, New York.
DeGroot, M. H., 1973. Doing what comes naturally: interpreting a tail area as a
posterior probability or as a likelihood ratio. J. Amer. Statist. Assoc. 68, 966-
969.
DeGroot, M. H., 1974. Reaching a consensus. 1. Amer. Statist. Assoc. 69, 118-
121.
Dempster, A. P., 1968. A generalization of Bayesian inference. J. Roy. Statist. Soc.
(Ser. B) 30, 205-248.
Dempster, A. P., 1973. The direct use of likelihood for significance testing. In
Proceedings of the Conference on Foundational Questions in Statistical Inference,
O. Barndorf'f-Nielsen et al. (Eds.). University of Aarhus, Aarhus.
Dempster, A. P., 1975. A subjectivist look at robustness. Bull. Int. Statist. Inst. 46,
349-374.
Dempster, A. P., 1976. Examples relevant to the robustness of applied inference.
In Statistical Decision Theory and Related Topics III, S. S. Gupta and J. Berger
Dempster, A. P., Laird, N. M., and Rubin, D. B., 1977. Maximum likelihood from
incomplete data via the EM algorithm (with discussion). 1. Roy. Statist. Soc.
(Ser. B) 39, 1-38.
Dempster, A. P., Selwyn, M. R., Patel, C. M., and Roth, A. J., 1984. Statistical and
computational aspects of mixed model analysis. Appl. Statist. 33, 203-214.
De Robertis, L., and Hartigan, J. A., 1981. Bayesian inference using intervals of
measures. Ann. Statist. 9, 235-244.
de Waal, D., Groenewald, P., van Zyl, D. and Zidek, J., 1985. Multi-Bayesian
estimation theory. Statistics and Decisions 3.
Dey, D. K., and Berger, J., 1983. On truncation of shrinkage estimators in simul-
taneous estimation of normal means. 1. Amer. Statist. Assoc. 78, 865-869.
Bibliography 579
Dey, D. K., and Srinivasan, C, 1985. Estimation of covariance matrix under Stein's
loss. Ann. Statist. 13.
Diaconis, P., and Freedman, D., 1980. Finite exchangeable sequences. Ann. Probab.
8,745-764.
Diaconis, P., and Freedman, D., 1981. On the statistics of vision: the Julesz
conjecture. 1. Math. Psych. 24, 112-138.
Diaconis, P., and Freedman, D., 1982. Bayes rules for location problems. In Statistical
Decision Theory and Related Topics lII, S. S. Gupta and J. Berger (Eds.).
Diaconis, P., and Freedman, D., 1983. Frequency properties of Bayes rules. In
Scientific Inference, Data Analysis, and Robustness, G. E. P. Box, T. Leonard,
and C F. Wu (Eds.). Academic Press, New York.
Diaconis, P., and Freedman, D., 1984. Partial exchangeability and sufficiency.
Technical Report, Department of Statistics, Stanford University, Stanford.
Diaconis, P., and Stein, C, 1983. Lectures on Statistical Decision Theory. Unpublished
Lecture Notes, Stanford University, Stanford.
Diaconis, P., and Y1visaker, D., 1979. Conjugate priors for exponential families.
Diaconis, P., and Ylvisaker, D., 1984. Quantifying prior opinions. In Bayesian
Statistics lI, J. M. Bernardo, M. H. DeGroot, D. V. Lindley, and A. F. M. Smith
Diaconis, P., and Zabell, S., 1982. Updating subjective probability. 1. Amer. Statist.
Assoc. 77, 822-830.
Diamond, G. A., and Forrester, J. S., 1983. Clinical trials and statistical verdicts:
probable grounds for appeal. Ann. Intern. Med. 98, 385-394.
Dickey, J. M., 1967. Expansions of t densities and related complete integrals. Ann.
Math. Statist. 38, 503-510.
Dickey, J. M., 1968. Three multidimensional integral identities with Bayesian appli-
cations. Ann. Math. Statist. 39, 1615-1627.
Dickey, J. M., 1971. The weighted likelihood ratio, linear hypotheses on normal
location parameters. Ann. Math. Statist. 42, 204-223.
Dickey, J. M., 1973. Scientific reporting. 1. Roy. Statist. Soc. (Ser. B) 35, 285-
305.
Dickey, J. M., 1974. Bayesian alternatives to the F-test and least-squares estimate
in normal linear model. In Studies in Bayesian Econometrics and Statistics, S.
E. Fienberg and A. Zellner (Eds.). North-Holland, Amsterdam.
Dickey, J. M., 1976. Approximate posterior distributions. 1. Amer. Statist. Assoc. 71,
680-689.
Dickey, J. M., 1977. Is the tail area useful as an approximate Bayes factor? 1. Amer.
Dickey, J. M., 1980a. Beliefs about beliefs, a theory of stochastic assessments of
subjective probabilities. In Bayesian Statistics, J. M. Bernardo, M. H. DeGroot,
D. V. Lindley, and A. F. M. Smith (Eds.). University Press, Valencia.
Dickey, J. M., 1980b. Approximate coherence for regression models with a new
analysis of Fisher's broadback wheatfield example. In Bayesian Analysis in
Econometrics and Statistics, A. Zellner (Ed.). North-Holland, Amsterdam.
Dickey, J. M., and Chong-Hong, c., 1984. Subjective-probability modeling with
elliptical distributions. In Bayesian Statistics lI, J. M. Bernardo, M. H. DeGroot,
D. Lindley, and A. Smith (Eds.). North-Holland, Amsterdam.
Dickey, J. M., and Freeman, P. R., 1975. Population-distributed personal prob-
abilities. 1. Amer. Statist. Assoc. 70, 362-364.
DuMouchel, W. M., and Harris, J. E., 1983. Bayes methods for combining the results
of cancer studies in humans and other species (with discussion). 1. Amer. Statist.
Assoc. 78, 293-315.
580 Bibliography
Dvoretsky, A., Wald, A., and Wolfowitz, J., 1951. Elimination of randomization in
certain statistical decision procedures and zero-sum two-person games. Ann.
Eaton, M. L., 1970. A complete class theorem for multidimensional one-sided
alternatives. Ann. Math. Statist. 41, 1884-1888.
Eaton, M. L., 1982. A method for evaluating improper prior distributions. In
Statistical Decision Theory and Related Topics III, S. S. Gupta and J. Berger
Eaton, M. L., 1983. Multivariate Statistics. Wiley, New York.
Eberl, W. Jr., and Moeschlin, 0., 1982. Mathematische Statisti/<. deGruyter, Berlin.
Edwards, A. W. F., 1972. Likelihood. Cambridge University Press, Cambridge.
Edwards, A. W. F., 1974. The history of likelihood. Int. Statist. Rev. 42, 9-15.
Edwards, W., 1968. Conservatism in human information processing. In Formal
Representation of Human Judgement, B. Kleinmuntz (Ed.). Wiley, New York.
Edwards, W., Lindman, H., and Savage, L. J., 1963. Bayesian statistical inference
for psychological research. Psychol. Rev. 70, 193-242.
Efron, 8., and Hinkley, D., 1978. Assessing the accuracy of the maximum likelihood
estimator: observed versus expected Fisher information. Biometrika 65, 457-
482.
Efron, B., and Morris, c., 1971. Limiting the risk of Bayes and empirical Bayes
estimators-Part I: the Bayes case. 1 Amer. Statist. Assoc. 66, 807-815.
Efron, 8., and Morris, c., 1972a. Limiting the risk of Bayes and empirical Bayes
estimators-Part II: The empirical Bayes case. J. Amer. Statist. Assoc. 67,
130-139.
Efron, 8., and Morris, C., 1972b. Empirical Bayes on vector observations-an
extension of Stein's method. Biometrika 59,335-347.
Efron, 8., and Morris, c., 1973. Stein's estimation rule and its competitors-an
empirical Bayes approach. J. Amer. Statist. Assoc. 68, 117-130.
Efron, 8., and Morris, C., 1976a. Families of minimax estimators of the mean of a
multivariate normal distribution. Ann. Statist. 4, 11-21.
Efron, B., and Morris, C., 1976b. Multivariate empirical Bayes and estimation of
covariance matrices. Ann. Statist. 4, 22-32.
Ellsburg, D., 1961. Risk, ambiguity, and the Savage axioms. Quart. 1 Econ. 75,
644-661.
Ewing, G. M., 1969. Calculus of Variations with Applications. Norton, New York.
Faith, R. E., 1978. Minimax Bayes and point estimators of a multivariate normal
mean. J. Multivariate Anal. 8, 372-379.
Fan, T. H., and Berger, J., 1990. Exact convolution of t-distributions, with application
to Bayesian inference for a normal mean with t prior distributions. J. Statist.
Computation and Simulation 36, 209-228.
Farrell, R. H., 1964. Estimators of a location parameter in the absolutely continuous
case. Ann. Math. Statist. 35, 949-998.
Farrell, R. H., 1966. Weak limits of sequences of Bayes procedures in estimation
theory. Proc. Fifth Berkeley Symp. Math. Statist. Probab. I, 83-111. University
of California Press, Berkeley.
Farrell, R. H., 1968a. Towards a theory of generalized Bayes tests. Ann. Math. Statist.
38, 1-22.
Farrell, R. H., 1968b. On a necessary and sufficient condition for admissibility of
estimators when strictly convex loss is used. Ann. Math. Statist. 38, 23-28.
Ferguson, T. S., 1967. Mathematical Statistics: A Decision-Theoretic Approach.
Ferguson, T. S., 1973. A Bayesian analysis of some nonparametric problems. Ann.
Statist. 1, 209-230.
Fine, T., 1973. Theories of Probability. Academic Press, New York.
Fishburn, P. c., 1964. Decision and Value Theory. Wiley, New York.
Bibliography 581
Fishburn, P. C., 1965. Analysis of decisions with incomplete knowledge of

probabilities. Oper. Res. 13,217-237.
Fishburn, P. c., 1981. Subjective expected utility: a review of normative theories.
Theory and Decision 13, 139-199.
Fishburn, P. c., Murphy, A. H., and Isaacs, H. H., 1968. Sensitivity of decisions to
probability estimation errors: a re-examination. Oper. Res. 16, 253-268.
Fisher, R. A., 1920. A mathematical examination of the methods of determining the
accuracy of an observation by the mean error, and by the mean square error.
Mon. Notic. Roy. Astron. Soc. 80, 757-770.
Fisher, R. A., 1922. On the mathematical foundations of theoretical statistics. Phi/os.
Trans. Roy. Soc. London (Ser. A) 222, 309-368.
Fisher, R. A., 1935. The fiducial argument in statistical inference. Ann. Eugenics 6,
391-398.
Fisher, R. A., 1959. Statistical Methods and Scientific Inference (2nd edn.). Oliver
and Boyd, Edinburgh.
Fraser, D. A. S., 1968. The Structure of Inference. Wiley, New York.
Fraser, D. A. S., 1977. Confidence, posterior probability, and the Buehler example.
Fraser, D. A. S., 1979. Inference and Linear Models. McGraw-Hill, New York.
Fraser, D. A. S., and Mackay, J., 1976. On the equivalence of standard inference
procedures. In Foundations of Probability Theory, Statistical Inference and
Statistical Theories of Science, Vol. II, W. L. Harper and C. A. Hooker (Eds.).
Reidel, Boston.
Freedman, D. A., and Purves, R. A., 1969. Bayes methods for bookies. Ann. Math.
Statist. 40, 1177-1186.
French, S. G., 1980. Updating of belief in the light of someone else's opinion. J.
Roy. Statist. Soc. (Ser. A) 143, 43-48.
French, S. G., 1981. Consensus of opinion. Eur. 1. Oper. Res. 7, 332-340.
French, S. G., 1984. Group consensus probability distributions: a critical survey. In
Bayesian Statistics II, J. M. Bernardo, M. H. DeGroot, D. V. Lindley, and
A. F. M. Smith (Eds.). North-Holland, Amsterdam.
Gardenfors, P., and Sahlin, N. E., 1982. Unreliable probabilities, risk taking, and
decision making. Synthese 53, 361-386.
Gatsonis, C. A., 1984. Deriving posterior distributions for a location parameter: a
decision-theoretic approach. Ann. Statist. 12, 958-970.
Gaver, D. P., and O'Muircheartaigh, I. G., 1987. Robust empirical Bayes analysis
of event rates. Technometrics 29, 1-15.
Geertsema, J. c., 1983. Recent views in the foundational controversy in statistics.
South African Statist. 1. 17, 121-146.
Geisser, S., 1971. The inferential use of predictive distributions. In Foundations of
Geisser, S., 1980. A predictivist primer. In Bayesian Analysis in Econometrics and
Statistics, A. Zellner (Ed.). North-Holland, Amsterdam.
Geisser, S., 1984a. On prior distributions for binary trials. American Statist. 38,
244-251.
Geisser, S., 1984b. On the prediction of observables: a selective update. In Bayesian
Geisser, S., and Eddy, W. F., 1979. A predictive approach to model selection. J.
Amer. Statist. Assoc. 74, 153-160.
Genest, c., 1984. A characterization theorem for externally Bayesian groups. Ann.
Statist. 12, 1100-1105.
Genest, c., and Schervish, M. 1985. Modelling expert judgements for Bayesian
updating. Ann. Statist. 13, 1198-1212.
582 Bibliography
George, E.!. 1986. Minimax multiple shrinkage estimation. Ann. Statist. 14, 188-205.
Ghia, G. D., 1976. Truncated generalized Bayes tests. Ph.D. Thesis, Department of
Statistics, Yale University, New Haven.
Ghosh, B. K., 1970. Sequential Tests of Statistical Hypotheses. Addison-Wesley,
Reading, Massachusetts.
Ghosh, J. K., Sinha, B. K., and Joshi, S. N., 1982. Expansions for posterior probability
and integrated Bayes risk. In Statistical Decision Theory and Related Topics III,
S. S. Gupta and J. Berger (Eds.). Academic Press, New York.
Ghosh, M., 1983. Estimates of multiple Poisson means: Bayes and empirical Bayes.
Statistics and Decisions 1, 183-195.
Ghosh, M., Hwang, J. T., and Tsui, K., 1983. Construction of improved estimators
in multiparameter estimation for discrete exponential families (with discussion).
Ann. Statist. 11, 351-376.
Ghosh, M., Hwang, J. T., and Tsui, K., 1984. Construction of improved estimators
in multiparameter estimation for continuous exponential families. J. Multi-
variate Anal. 14, 212-220.
Ghosh, M., and Meeden, G., 1977. Admissibility of linear estimators in the one-
parameter exponential family. Ann. Statist. 5, 772-778.
Ghosh, M., and Meeden, G., 1984. A new Bayesian analysis of a random effects
model. J. Roy. Statist. Soc. (Ser. B) 83.
Gilliland, D. c., Boyer, J. E., Jr., and Tsao, H. J., 1982. Bayes empirical Bayes:
finite parameter case. Ann. Statist. 10, 1277-1282.
Giron, F. J., and Rios, S., 1980. Quasi-Bayesian behavior: a more realistic approach
to decision making? In Bayesian Statistics II, J. M. Bernardo, M. H.
DeGroot, D. V. Lindley, and A. F. M. Smith (Eds.). University Press, Valencia.
Gitting, J. c., 1979. Bandit processes and dynamic allocation indices (with dis-
cussion).1. Roy. Statist. Soc. (Ser. B) 41, 148-177.
Gieser, L. J., 1979. Minimax estimation ofa normal mean vector when the covariance
matrix is unknown. Ann. Statist. 7, 838-846.
Goel, P. K., 1983. Information measures and Bayesian hierarchical models. J. Amer.
Goel, P. K., and DeGroot, M. H., 1981. Information about hyperparameters in
hierarchical models. J. Amer. Statist. Assoc. 76, 140-147.
Goldstein, M., 1980. The linear Bayes regression estimator under weak prior
assumptions. Biometrika 67, 621-628.
Goldstein, M., 1981. Revising previsions: a geometric interpretation (with
discussion). J. Roy. Statist. Soc. (Ser. B) 43, 105-130.
Goldstein, M., 1984. Separating beliefs. In Bayesian Inference and Decision
Techniques with Applications: Essays in Honor of Bruno de Finetti, P. K. Goel
and A. Zellner (Eds.). North-Holland, Amsterdam.
Good, I. J., 1950. Probability and the Weighing of Evidence. Charles Griffin,
London.
Good, I. J., 1952. Rational decisions. J. Roy. Statist. Soc. (Ser. B) 14, 107-114.
Good, I. J., 1953. On the popUlation frequencies of species and the estimation of
population parameters. Biometrika 40, 237-264.
Good, I. J., 1958. Significance tests in parallel and in series. 1. Amer. Statist. Assoc.
53,799-813.
Good, I. J., 1962. Subjective probability as a measure of a non measurable set. In
Logic, Methodology and Philosophy of Science. Stanford University Press,
Stanford, California.
Good, I. J., 1965. The Estimation of Probabilities: An Essay on Modern Bayesian
Methods. M.LT. Press, Cambridge, Massachusetts.
Bibliography 583
Good, I. J., 1973. The probabilistic explication of evidence, surprise, causality,

explanation, and utility. In Foundations of Statistical Inference, V. P. Godambe
and D. A. Sprott (Eds.). Holt, Rinehart, and Winston, Toronto.
Good, I. J., 1976. The Bayesian influence, or how to sweep subjectivism under the
carpet. In Foundations of Probability Theory, Statistical Inference, and Statistical
Theories of Science, Vol. II, W. L. Harper and C. A. Hooker (Eds.). Reidel,
Boston.
Good, I. J., 1980. Some history of the hierarchical Bayesian methodology. In Bayesian
(Eds.). University Press, Valencia.
Good, I. J., 1983a. Good Thinking: The Foundations of Probability and Its Applications.
University of Minnesota Press, Minneapolis.
Good, I. J., 1983b. The robustness of a hierarchical model for multinomials and
contingency tables. In Scientific Inference, Data Analysis, and Robustness,
G. E. P. Box, T. Leonard, and C. F. Wu (Eds.). Academic Press, New
York.
Good, I. J., 1984. Notes C140, C144, C199, C200, and C201. J. Statist. Comput.
Simul. 18, 19, 20.
Govindarajulu, Z., 1981. The Sequential Statistical Analysis of Hypothesis Testing,
Point and Interval Estimation, and Decision Theory. American Sciences Press,
Columbus, Ohio.
Gupta, S. S. and Hsiao, P., 1981. On r -minimax, minimax, and Bayes procedures
for selecting populations close to a control. Sankhya (Ser. B) 43, 291-318.
Gupta, S. S. and Miescke, K. J., 1984. Sequential selection procedures-a decision-
theoretic approach. Ann. Statist. 12, 336-350.
Gupta, S. S., and Panchapakesan, S., 1979. Multiple Decision Procedures: Theory
and Methodology of Selecting and Ranking Populations. Wiley, New York.
Gutmann, S., 1982a. Stein's paradox is impossible in problems with finite sample
space. Ann. Statist. 10, 1017-1020.
Gutmann, S., 1982b. Stein's paradox is impossible in the nonanticipative context.
J. Amer. Statist. Assoc. 77, 934-935.
Haft, L. R., 1976. Minimax estimators of the multinormal mean: autoregressive
priors. 1. Multivariate Anal. 6, 265-280.
Haft, L. R., 1977. Minimax estimators for a multinormal precision matrix. J. Multi-
variate Anal. 7, 374-385.
Haft, L. R., 1978. The multivariate normal mean with intraclass correlated
components: estimation of urban fire alarm probabilities. J. Amer. Statist. Assoc.
60, 806-825.
Haft, L. R., 1980. Empirical Bayes estimation of the multivariate normal covariance
matrix. Ann. Statist. 8, 586-597.
Half, L. R., and Johnson, R. W., 1986. The superharmonic condition for simultaneous
estimation of means in exponential families. Canad. J. Statist. 14,43-54.
Hald, A., 1971. The size of Bayes and minimax tests as function of the sample size
and loss ratio. Skand. Aktuar Tidskr., 53-73.
Halmos, P. R., 1950. Measure Theory. van Nostrand, New York. Second edition
1974. Springer-Verlag, New York.
Hammersley, J. M., and Handscomb, D. c., 1964. Monte Carlo Methods. Wiley,
New York.
Hartigan, J., 1964. Invariant prior distributions. Ann. Math. Statist. 35, 836-845.
Hartigan, J. A., 1969. Linear Bayesian methods. 1. Roy. Statist. Soc. (Ser. B) 31,
446-454.
Hartigan, J. A., 1983. Bayes Theory. Springer-Verlag, New York.
584 Bibliography
Heath, D., and Sudderth, W., 1978. On finitely additive priors, coherence, and
extended admissibility. Ann. Statist. 6, 333-345.
Heyde, C. C., and Johnstone, I. M., 1979. On asymptotic posterior normality for
stochastic processes. J. Roy. Statist. Soc. (Ser. B) 41, 184-189.
Hildreth, c., 1963. Bayesian statisticians and remote clients. Econometrica 31,
422-438.
Hill, B., 1965. Inference about variance components in the one-way model. J. Amer.
Hill, B., 1974. On coherence, inadmissibility, and inference about many parameters
in the theory of least squares. In Studies in Bayesian Econometrics and Statistics,
S. Fienberg and A. Zellner (Eds.). North-Holland, Amsterdam.
Hill, B., 1975. A simple general approach to inference about the tail of a distribution.
Ann. Statist. 3, 1163-1174.
Hill, B., 1977. Exact and approximate Bayesian solutions for inference about variance
components and multivariate inadmissibility. In New Developments in the
Application of Bayesian Methods, A. Aykac and C. Brumat (Eds.). North-
Holland, Amsterdam.
Hill, B., 1980a. Robust analysis of the random model and weighted least squares
regression. In Evaluation of Econometric Models. Academic Press, New
York.
Hill, B., 1980b. Invariance and robustness of the posterior distribution of characteris-
tics of a finite population, with reference to contingency tables and the sampling
of species. In Bayesian Analysis in Econometrics and Statistics, A. Zellner (Ed.).
North-Holland, Amsterdam.
Hill, B., 1982. Comment on "Lindley's Paradox," by G. Shafer. J. Amer. Statist.
Assoc. 77, 344-347.
Hill, B., and Lane, D., 1984. Conglomerability and countable additivity. In Bayesian
Inference and Decision Techniques with Applications, P. K. Goel and A. Zellner
Hinde, J., and Aitkin, M., 1986. Canonical likelihoods: a new likelihood treatment
of nuisance parameters. Biometrika 74, 45-58.
Hinkley, D. V., 1979. Predictive likelihood. Ann. Statist. 7, 718-728.
Hinkley, D. V., 1983. Can frequentist inference be very wrong? A conditional "yes".
In Scientific Inference, Data Analysis, and Robustness, G. E. P. Box et al. (Eds.).
Hirschmann, I. I., and Widder, D. V., 1955. The Convolution Transform. Princeton
University Press, Princeton, N.J.
Hoadley, B. 1981. Quality management plan (QMP). Bell System Tech. J. 60, 215-
273.
Hodges, J. L. Jr., and Lehmann, E. L., 1952. The use of previous experience in
reaching statistical decisions. Ann. Math. Statist. 23, 396-407.
Hodges, J. L. Jr., and Lehmann, E. L., 1954. Testing the approximate validity of
statistical hypotheses. 1. Roy. Statist. Soc. (Ser. B) 16, 261-268.
Hoeffding; W., 1960. Lower bounds for the expected sample size and the average
risk of a sequential procedure. Ann. Math. Statist. 31, 352-368.
Hoffman, K., 1984. Admissibility and inadmissibility of estimators in the one-
parameter exponential family. Math. Oper. Statist.
Hogarth, R. M., 1975. Cognitive processes and the assessment of subjective probabil-
ity distributions. J. Amer. Statist. Assoc. 70, 271-294.
Hooper, P. M., 1982. Invariant confidence sets with smallest expected measure. Ann.
Statist. 10, 1283-1294.
Hora, R. B., and Buehler, R. J., 1966. Fiducial theory and invariant estimation. Ann.
Bibliography 585
Howard, R. A., and Matheson, J. E., 1984. Influence diagrams. In The Principles and
Applications of Decision Analysis, Vol. II, R. A. Howard and J. E. Matheson
(Eds.). Strategic Decisions Group, Menlo Park, California.
Huber, P. J., 1972. Robust statistics: a review. Ann. Math. Statist. 43, 1041-1067.
Huber, P. J., 1973. The use of Choquet capacities in statistics. Bull. Int. Statist. Inst.
45,181-191.
Huber, P. J., 1981. Robust Statistics. Wiley, New York.
Hudson, H. M., 1974. Empirical Bayes estimation. Technical Report # 58, Depart-
ment of Statistics, Stanford University, Stanford, California.
Hudson, H. M., 1978. A natural identity for exponential families with applications
in multivariate estimation. Ann. Statist. 6, 473-484.
Hudson, H. M., 1985. Adaptive estimators for simultaneous estimation of Poisson
means. Ann. Statist. 13, 246-261.
Hui, S., and Berger, J., 1983. Empirical Bayes estimation of rates in longitudinal
studies. J. Amer. Statist. Assoc. 78, 753-760.
Huzurbazar, V. S., 1976. Sufficient Statistics. Marcel Dekker, New York.
Hwang, J. T., 1982a. Improving upon standard estimators in discrete exponential
families with applications to Poisson and negative binomial cases. Ann. Statist.
10, 857-867.
Hwang, J. T., 1982b. Semi-tail upper bounds on the class of admissible estimators
in discrete exponential families, with applications to Poisson and negative
binomial distributions. Ann. Statist. 10, 1137-1147.
Hwang, J. T., 1982c. Certain bounds on the class of admissible estimators in
continuous exponential families. In Statistical Decision Theory and Related
Topics III, S. S. Gupta and J. Berger (Eds.). Academic Press, New York.
Hwang, J. T., 1985. Universal domination and stochastic domination-decision
theory simultaneously under a broad class of loss functions. Ann. Statist. 13,
295-314.
Hylland, A., and Zeckhauser, R., 1981. The impossibility of Bayesian group decision
making with separate aggregation of beliefs and values. Econometrica 79,
1321-1336.
Ighodaro, A., Santner, T., and Brown, L., 1982. Admissibility and complete class
results for the multinomial estimation problems with entropy and squared-error
loss. J. Multivariate Anal. 12, 469-479.
Isii, K., and Noda, K., 1985. A vector space approach to obtaining a condition for
the admissibility of statistical decision functions. Statistical Theory and Decision
Analysis. K. Matusita (Ed.). North-Holland, Amsterdam, pp. 291-313.
Jackson, D. A., Donovan, T. M., Zimmer, W. J., and Deely, J. J., 1970. r -minimax
estimators in the exponential family. Biometrika 57,439-443.
Jackson, P. H., Novick, M. R., and Thayer, D. T., 1971. Estimating regressions in
m-groups. Brit. J. Math. Statist. Psychol. 24, 129-153.
James, W., and Stein, c., 1960. Estimation with quadratic loss. In Proc. Fourth
Berkeley Symp. Math. Statist. Probab. 1,361-380. University of California Press,
Berkeley.
Jaynes, E. T., 1968. Prior probabilities. IEEE Transactions on Systems Science and
Cybernetics, SSC-4, 227-241.
Jaynes, E. T., 1980. Marginalization and prior probabilities. In Bayesian Analysis
in Econometrics and Statistics, A. Zellner (Ed.). North-Holland, Amsterdam.
Jaynes, E. T., 1983. Papers on Probability, Statistics, and Statistical Physics. A reprint
collection. R. D. Rosenkrantz (Ed.). Reidel, Dordrecht.
Jeffrey, R., 1968. Probable knowledge. In The Problem of Inductive Logic, I. Lakatos
Jeffrey, R., 1983. The Logic of Decision (2nd edn.). University of Chicago Press,
Chicago.
586 Bibliography
Jeffreys, H., 1957. Scientific Inference. Cambridge University Press, London.

Jeffreys, H., 1961. Theory of Probability (3rd edn.). Oxford University Press, London.
Jennrich, R. I., and Sampson, P. F., 1976. Newton-Raphson and related algorithms
for maximum likelihood variance component estimation. Technometrics 18,
11-18.
Jewell, W. S., 1979. Stochastically-ordered parameters in Bayesian prediction. Report
ORC 79-12, Operations Research Center, University of California, Berkeley.
Jewell, W. S., 1983. Enriched multinormal priors revisited. Technical Report.
Operations Research Center, University of California, Berkeley.
Jewell, W. S., and Schnieper, 1985. Credibility approximations for Bayesian predic-
tion of second moments. Astin Bulletin 15, 103-121.
Johnson, R. A., 1967. An asymptotic expansion for posterior distributions. Ann.
Math. Statist. 38, 1899-1906.
Johnson, R. A., 1970. Asymptotic expansions associated with posterior distributions.
Johnson, R. W., 1984. Simultaneous estimation of generalized Pearson means. Ph.D.
Thesis, Department of Mathematics, University of California, San Diego.
Johnstone, I., 1984. Admissibility, difference equations, and recurrence in estimating
a Poisson mean. Ann. Statist. 12, 1173-1198.
Johnstone, I., 1985. Admissible estimation, Dirichlet principles and recurrence of
birth-death chains in Z~. Z. Wahrsch. verw. Gebiete 69.
Johnstone, I., and Lalley, S., 1984. On independent statistical decision problems
and products of diffusions. Z. Wahrsch. verw. Gebiete. 68, 29-47.
Johnstone, I., and Velleman, P., 1985. Efficient scores, variance decompositions, and
Monte Carlo swindles. J. Amer. Statist. Assoc. 80, 851-862.
Jones, A. J., 1980. Game Theory: Mathematical Models of Conflict. Wiley, New York.
Joshi, V. M., 1969. On a theorem of Karlin regarding admissible estimates for
exponential populations. Ann. Math. Statist. 40, 216-223.
Judge, G., and Bock, M. E., 1978. Implications of Pre-Test and Stein Rule Estimators
in Econometrics. North-Holland, Amsterdam.
Kadane, J. B., 1980. Predictive and structural methods for eliciting prior distributions.
In Bayesian Analysis in Econometrics and Statistics, A. Zellner (Ed.). North-
Holland, Amsterdam.
Kadane, J. B., 1984. Robustness of Bayesian Analyses. North-Holland, Amsterdam.
Kadane, J. B., and Chuang, D. T., 1978. Stable decision problems. Ann. Statist. 6,
1095-1110.
Kadane, J. B., Dickey, J. M., Winkler, R. L., Smith, W. S., and Peters, S. c., 1980.
Interactive elicitation of opinion for a normal linear model. J. Amer. Statist.
Assoc. 75, 845-854.
Kahneman, D., Slovic, P., and Tversky, A., 1982. Judgement Under Uncertainty:
Heuristics and Biases. Cambridge University Press, New York.
Karlin, S., 1956. Decision theory of P6lya type distributions: case of two actions,
I. In Proc. Third Berkeley Symp. on Statist. Probab. 1, 115-129. University of
California Press, Berkeley.
Karlin, S., 1957a. P6lya type distributions, II. Ann. Math. Statist. 28, 281-308.
Karlin, S., 1957b. P6lya type distributions, III: admissibility for multi-action
problems. Ann. Math. Statist. 28, 839-860.
Karlin, S., 1958. Admissibility for estimation with quadratic loss. Ann. Math. Statist.
29, 406-436.
Karlin, S., and Rubin, H., 1956. The theory of decision procedures for distributions
with monotone likelihood ratio. Ann. Math. Statist. 27, 272-299.
Keener, R. W., 1980. Renewal theory and the sequential design of experiments with
two states of nature. Commun. Statist. A9(16), 1699-1726.
Bibliography 587
Keener, R. W., 1984. Second-order efficiency in the sequential design of experiments.

Ann. Statist. 12, 510-532.
Keeney, R. L., and Raiffa, H., 1976. Decisions with Multiple Objectives. Wiley, New
York.
Kelley, T. L., 1927. The Interpretation of Educational Measurements. World Books,
New York.
Kempthorne, P. J., 1983. Minimax-Bayes compromise estimators. In Business
and Economics Statistics Proceedings of the American Statistical Association,
Washington, D.C.
Kempthorne, P. 1., 1987. Numerical specification of discrete least favorable prior
distributions. SIAM J. Sci. Statist. Comput. 8, 171-184.
Kiefer, 1., 1957. Invariance, minimax sequential estimation, and continuous time
processes. Ann. Math. Statist. 28, 573-601.
Kiefer, J., 1966. Multivariate optimality results. In Multivariate Analysis, P. R.
Krishnaiah (Ed.). Academic Press, New York.
Kiefer, J., 1976. Admissibility of conditional confidence procedures. Ann. Statist. 4,
836-865.
Kiefer, J., 1977a. Conditional confidence statements and confidence estimators
(theory and methods). 1. Amer. Statist. Assoc. 72, 789-827.
Kiefer, J., 1977b. The foundations of statistics-are there any? Synthese 36, 161-176.
Kiefer, 1., and Sacks, J., 1963. Asymptotically optimum sequential inference and
design. Ann. Math. Statist. 34, 705-750.
Kloeck, T., and van Dijk, H. K., 1978. Bayesian estimates of equation system
parameters; an application of integration by Monte Carlo. Econometrica 46,
1-19.
Kozek, A., 1982. Towards a calculus for admissibility. Ann. Statist. 10, 825-837.
Kraft, C. H., Pratt, 1. W., and Seidenberg, A., 1959. Intuitive probability on finite
sets. Ann. Math. Statist. 30, 408-419.
Kudo, H., 1955. On minimax invariant estimates of the transformation parameter.
Natural Science Report 6,31-73, Ochanomizu University, Japan.
Kudo, H., 1967. On partial prior information and the property of parametric
sufficiency. Proc. Fifth Berkeley Symp. Statist. Probab. 1, University of California
Press, Berkeley.
Kuo, L., 1983. Bayesian bio-assay design. Ann. Statist. 11, 886-895.
Kuo, L., 1986. Computation of mixtures of Dirichlet processes. SIAM J. Sci. Statist.
Comput. 7, 60-71.
Kusama, T., 1966. Remarks on admissibility of decision functions. Ann. Inst. Statist.
Math. 18, 141-148.
Laird, N. M., 1978. Nonparametric maximum likelihood estimation of a mixing
distribution. J. Amer. Statist. Assoc. 73, 805-811.
Laird, N. M., 1982. The computation of estimates of variance components using
the EM algorithm. J. Statist. Comput. Simul. 14, 295-303.
Laird, N. M., 1983. Empirical Bayes estimates using the nonparametric maximum
likelihood estimate for the prior. 1. Statist. Comput. Simul. IS, 211-220.
La Motte, L. R., 1982. Admissibility in linear estimation. Ann. Statist. 10,245-255.
Lane, D. A., and Sudderth, W. D., 1983. Coherent and continuous inference. Ann.
Statist. 11, 114-120.
Laplace, P. S., 1812. Theorie Analytique des Probabilites. Courcier, Paris.
Larson, R. E., and Casti, J. L., 1978 and 1982. Principles of Dynamic Programming,
Parts I and II. Marcel Dekker, New York.
Lauritzen, S. L., 1982. Statistical Models As Extremal Families. University Press,
Aalborg.
Lauritzen, S. L., 1984. Extreme point models in statistics. Scand. 1. Statist. 11,
65-91.
588 Bibliography
Leamer, E. E., 1978. Specification Searches. Wiley, New York.

Leamer, E. E., 1982. Sets of posterior means with bounded variance prior.
Econometrica 50, 725-736.
LeCam, L., 1955. An extension of Wald's theory of statistical decision functions.
LeCam, L., 1956. On the asymptotic theory of estimation and testing hypotheses.
Proc. Third Berkeley Symp. Math. Statist. Probab. 1, University of California
Press, Berkeley.
LeCam, L., 1974. Notes on asymptotic methods in statistical decision theory. Centre
de Recherches Mathematiques, Universite de Montreal.
LeCam, L., 1977. A note on metastatistics or "an essay toward stating a problem
in the doctrine of chances." Synthese 36, 133-160.
Lehmann, E. L., 1947. On families of admissible tests. Ann. Math. Statist. IS, 97-104.
Lehmann, E. L., 1959, 1985. Testing Statistical Hypotheses, 1st edn. (1959); 2nd edn.
to appear. Wiley, New York.
Lehmann, E. L., 1983. Theory of Point Estimation. Wiley, New York.
Lehn, J., and Rummel, F., 1985. Gamma-minimax estimation ofa binomial probabil-
ity under squared-error loss. Statistics and Decisions 3.
Lempers, F. 8., 1971. Posterior Probabilities of Alternative Linear Models. University
of Rotterdam Press, Rotterdam.
Leonard, T., 1976. Some alternative approaches to multiparameter estimation.
Biometrika 63, 69-76.
Leonard, T., 1984. Some data-analytic modifications to Bayes-Stein estimation. Ann.
Inst. Statist. Math. 36, 11-22.
Lepage, R., 1979. Smoothing Wald's test. Technical Report, Department of Statistics,
Michigan State University, East Lansing.
Lin, P. E., and Mousa, A., 1983. Minimax estimation of a multivariate normal mean
under a convex loss function. Australian 1 Statist. 25, 463-466.
Lindley, D. V., 1957. A statistical paradox. Biometrika 44, 187-192.
Lindley, D. V., 1961. The use of prior probability distributions in statistical inference
and decision. In Proc. Fourth Berkeley Symp. Math. Statist. Probab. University
Lindley, D. V., 1965. Introduction to Probability and Statistics from a Bayesian
Viewpoint (Parts 1 and 2). Cambridge University Press, Cambridge.
Lindley, D. V., 1971a. Bayesian Statistics, A Review. SIAM, Philadelphia.
Lindley, D. V., 1971b. The estimation of many parameters. In Foundations of
Lindley, D. V., 1977. A problem in forensic science. Biometrika 64, 207-213.
Lindley, D. V., 1980. Approximate Bayesian methods. In Bayesian Statistics II,
l M. Bernardo, M. H. DeGroot, D. V. Lindley, and A. F. M. Smith (Eds.).
Valencia Press, Valencia.
Lindley, D. V., 1982a. Scoring rules and the inevitability of probability. Int. Statist.
Rev. 50, 1-26.
Lindley, D. V., 1982b. The improvement of probability judgements. J. Roy. Statist.
Soc. (Ser. A) 145, 117-126.
Lindley, D. V., 1984. Reconciliation of discrete probability distributions. In Bayesian
Statistics II, J. Bernardo, M. H. DeGroot, D. V. Lindley, and A. F. M. Smith
(Eds.). Valencia Press, Valencia.
Lindley, D. V., and Novick, M. R., 1981. The role of exchangeability in inference.
Lindley, D. V., and Phillips, L. D., 1976. Inference for a Bernoulli process (a Bayesian
view). Amer. Statist. 30, 112-119.
Bibliography 589
Lindley, D. V., and Singpurwalla, N. D., 1986. Reliability and fault tree analysis
using expert opinions. J. Amer. Statist. Assoc. 81, 87-90.
Lindley, D. V., and Smith, A. F. M., 1972. Bayes estimates for the linear model. 1.
Roy. Statist. Soc. (Ser. B) 34, 1-41.
Lindley, D. V., Tversky, A., and Brown, R. V., 1979. On the reconciliation of
probability assessments (with discussion). J. Roy. Statist. Soc. (Ser. A) 142,
146-180.
Lindsay, B. G., 1981. Properties of the maximum likelihood estimator of a mixing
distribution. In Statistical Distributions in Scientific Work, C. Taillie et al. (Eds.).
Vol. 5, 95-109.
Lindsay, B. G., 1983. The geometry of mixture likelihoods, Part II: the exponential
family. Ann. Statist. 11, 783-792.
Lord, F. M., 1969. Estimating true-score distributions in psychological testing (an
empirical Bayes estimation problem). Psychometrika 34,259-299.
Lord, F. M., and Cressie, N., 1975. An empirical Bayes procedure for finding an
interval estimate. Sankhyii (Ser. B) 37, 1-9.
Lorden, G., 1977. Nearly-optimal sequential tests for finitely many parameter values.
Lorden, G., 1984. Nearly optimal sequential tests for exponential families. Technical
Report, Department of Mathematics, California Institute of Technology,
Pasadena.
Louis, T. A., 1982. Finding the observed information matrix when using the EM
algorithm. J. Roy. Statist. Soc. (Ser. B) 44, 226-233.
Louis, T. A., 1984. Estimating a population of parameter values using Bayes and
empirical Bayes methods. J. Amer. Statist. Assoc. 79, 393-398.
Luce, R. D., and Raiffa, H., 1957. Games and Decisions. Wiley; New York.
Lush, J. L., 1937. Animal Breeding Plans. Iowa State University Press,
Ames.
Magwire, C. A., 1953. Sequential decisions involving the choice of experiments.
Ph.D. Thesis, Stanford University, Stanford, California.
Mandelbaum, A., 1984. All admissible linear estimators of the mean of a Gaussian
distribution on a Hilbert space. Ann. Statist. 10, 1448-1466.
Marazzi, A., 1985. On constrained minimization of the Bayes risk for the linear
model. Statistics and Decisions 3.
Marden, J. I., 1982. Minimal complete classes of tests of hypotheses with multivariate
one-sided alternatives. Ann. Statist. 10, 962-970.
Marden, J. I., 1983. Admissibility of invariant tests in the general multivariate
analysis of variance problem. Ann. Statist. 11, 1086-1099.
Maritz, J. S., 1970. Empirical Bayes Methods. Methuen, London.
Martz, H. F., and Waller, R. A., 1982. Bayesian Reliability Analysis. Wiley, New
York.
Matthes, T. K., and Truax, D. R., 1967. Tests of composite hypotheses for the
multivariate exponential family. Ann. Math. Statist. 38, 681-697.
McConway, K. J., 1981. Marginalization and linear opinion pools. J. Amer. Statist.
Assoc. 76, 410-414.
Meeden, G., and Ghosh, M., 1981. Admissibility in finite problems. Ann. Statist. 9,
846-852.
Meeden, G., and Isaacson, D., 1977. Approximate behavior of the posterior
distribution for a large observation. Ann. Statist. 5, 899-908.
Meinhold, R. 1., and Singpurwalla, N. D., 1983. Bayesian analysis of a com-
monly used model for describing software failure. The Statistician 32, 168-
173.
590 Bibliography
Menges, G., 1966. On the Bayesification of the minimax principle. Unternehmens-

forschung 10, 81-91.
Morris, c., 1977. Interval estimation for empirical Bayes generalizations of Stein's
estimator. In Proceedings of the 22nd Conference on the Design of Experiments
in Army Research Development and Testing. (ARO Report 77-2).
Morris, c., 1982. Natural exponential families with quadratic variance functions.
Morris, c., 1983a. Parametric empirical Bayes inference: Theory and applications.
J. Amer. Statist. Assoc. 78, 47-65.
Morris, C., 1983b. Parametric empirical Bayes confidence sets. In Scientific Inference,
Data Analysis, and Robustness, G. E. P. Box, T. Leonard, and C. F. Wu (Eds.).
Morris, P. A, 1977. Combining expert judgements: a Bayesian approach. Manage.
Sci. 23, 679-693.
Morris, P. A., 1983. An axiomatic approach to expert resolution. Manage. Sci. 29,
24-31.
Muirhead, R. J., 1982. Aspects of Multivariate Statistical Theory. Wiley, New York.
Nachbin, L., 1965. The Haar Integral. van Nostrand, New York.
Nash, J. F. Jr., 1950. The bargaining problem. Econometrica 18, 155-162.
Naylor, J. c., and Smith, A F. M., 1982. Applications of a method for the efficient
computation of posterior distributions. Appl. Statist. 31, 214-225.
Naylor, J. C., and Smith, A F. M., 1983. A contamination model in clinical chemistry:
an illustration of a method for -the efficient computation of posterior
distributions. The Statistician 32, 82-87.
Nelson, W., 1966. Minimax solution of statistical decision problems by iteration.
Neyman, J., 1957. "Inductive behavior" as a basic concept of philosophy of science.
Rev. Math. Statist. Inst. 25, 7-22.
Neyman, J., 1967. A Selection of Early Statistical Papers of J. Neyman. University
Neyman, J., 1977. Frequentist probability and frequentist statistics. Synthese 36,
97-131.
Neyman, J., and Pearson, E. S., 1933. On the problem of the most efficient tests of
statistical hypotheses. Phi/os. Trans. Roy. Soc. (Ser. A) 231, 289-337.
Novick, M. R., and Hall, W. J., 1965. A Bayesian indifference procedure. J. Amer.
Statist. Assoc. 60,1104-1117.
Novick, M. R., Jackson, P. H., Thayer, D. T., and Cole, N. S., 1972. Estimating
multiple regressions in m-groups; a cross-validation study. Brit. 1. Math. Statist.
Psychol. 25, 33-50.
O'Bryan, T. E., 1979. Rates of convergence in a modified empirical Bayes estimation
problem involving Poisson distributions. Commun. Statist.- Theory and
Methods A8, 167-174.
O'Hagan, A, 1979. On outlier rejection phenomena in Bayes inference. 1. Roy.
Statist. Soc. (Ser. B) 41, 358-367.
O'Hagan, A, 1981. A moment of indecision. Biometrika 68, 329-330.
Olkin, I., and Selliah, J. B., 1977. Estimating covariance in a multivariate normal
distribution. In Statistical Decision Theory and Related Topics II, S. S. Gupta
and D. S. Moore (Eds.). Academic Press, New York.
Oman, S. D., 1983. A class of modified Stein estimators with easily computable risk
functions. J. Statist. Planning and Inference 7, 359-369.
Peng, J. C. M., 1975. Simultaneous estimation of the parameters of independent
Poisson distributions. Technical Report No. 78, Department of Statistics,
Stanford University, Stanford, California.
Pilz, J., 1983. Bayesian Estimation and Experimental Design in Linear Regression
Models. Teubner-Texte, Leipzig.
Bibliography 591
Pitman, E. J. G., 1939. The estimation of location and scale parameters of a

continuous population of any given form. Biometrika 30,391-421.
Polasek, W., 1982. Local sensitivity analysis and matrix derivatives. In Operations
Research in Progress, G. Feichtinger et al. (Eds.). Reidel, Dordrecht.
Polasek, W., 1984. Multivariate regression systems: Estimation and sensitivity
analysis of two-dimensional data. In Robustness of Bayesian Analyses, J. Kadane
Polasek, W., 1985. Sensitivity analysis for general and hierarchical linear regression
models. In Bayesian Inference and Decision Techniques with Applications, P. K.
Goel and A. Zellner (Eds.). North-Holland, Amsterdam.
Portnoy, S., 1971. Formal Bayes estimation with application to a random effects
model. Ann. Math. Statist. 42, 1379-1402.
Portnoy, S., 1972. On fundamental theorems in decision theory. Unpublished Notes,
Department of Statistics, Harvard University, Cambridge, Massachusetts.
Pratt, J. W., 1962. Discussion of A. Birnbaum's "On the foundations of statistical
inference." 1. Amer. Statist. Assoc. 57, 269-326.
Pratt, J. W., 1965. Bayesian interpretation of standard inference statements (with
discussion). 1. Roy. Statist. Soc. (Ser. B) 27, 169-203.
Pratt, J. W., Raiffa, H., and Schlaifer, R., 1965. Introduction to Statistical Decision
Theory (preliminary edn.). McGraw-Hill, New York.
Press, S. J., 1978. Qualitative controlled feedback for forming group judgements
and making decisions. 1 Amer. Statist. Assoc. 73, 526-535.
Press, S. J., 1980. Bayesian computer programs. In Bayesian Analysis in Econometrics
and Statistics, A. Zellner (Ed.). North-Holland, Amsterdam.
Press, S. J., 1982. Applied Multivariate Analysis: Using Bayesian and Frequentist
Measures of Inference (2nd edn.). Kreiger, New York.
Press, S. J., 1984. Multivariate analysis (Bayesian). In Encyclopedia of Statistical
Sciences, N. Johnson and S. Kotz (Eds.). Wiley, New York.
Press, S. J., and Shigemasu, K., 1984. Bayesian MANOVA and MANOCOVA under
exchangeability. Can. 1. Statist 12.
Proschan, F., and Singpurwalla, N. D., 1979. Accelerated life testing-a pragmatic
Bayesian approach. In Optimization in Statistics, J. Rustagi (Ed.). Academic
Press, New York.
Proschan, F., and Singpurwalla, N. D., 1980. A new approach to inference from
accelerated life tests. IEEE Transactions of Reliability R-29, 98-102.
Rabena, M., 1983. Sensitivity analysis in Bayesian decision. Publicacione # 2,
Departamento de Bioestadistica, Universidad de Valencia.
Raiffa, H., 1968. Decision Analysis: Introductory Lectures on Choices under
Uncertainty. Addison-Wesley, Reading, Massachusetts.
Raiffa, H., and Schlaifer, R., 1961. Applied Statistical Decision Theory. Division of
Research, Graduate School of Business Administration, Harvard University,
Boston.
Ralescu, D., and Ralescu, S., 1981. A class of nonlinear admissible estimators in
the one-parameter exponential family. Ann. Statist. 9, 177-183.
Ramsay, J. 0., and Novick, M. R., 1980. PLU robust Bayesian decision theory:
point estimation. 1. Amer. Statist. Assoc. 75, 901-907.
Ramsey, F. P., 1926. Truth and probability. Reprinted in Studies in Subjective
Probability, H. E. Kyburg and H. E. Smokier (Eds.). Wiley, New York.
Rao, C. R., 1976. Estimation of parameters in a linear model. Ann. Statist. 4,
1023-1037.
Rao, C. R., 1977. Simultaneous estimation of parameters-a compound decision
problem. In Statistical Decision Theory and Related Topics II, S. S. Gupta and
D. S. Moore (Eds.). Academic Press, New York.
Ray, S. N., 1965. Bounds on the maximum sample size of a Bayes sequential
procedure. Ann. Math. Statist. 36, 859-878.
592 Bibliography
Reilly, A., and Sedransk, N., 1984. Bayesian analysis of growth curves. Technical
Report, Department of Mathematics and Statistics, State University of New
York, Albany.
Reinsel, G. c., 1985. Mean square error properties of empirical Bayes estimators in
a multivariate random effects generalized linear model. J. Amer. Statist. Assoc.
SO, 642-650.
Reinsel, G. c., 1984. Estimation and prediction in a multivariate random effects
generalized linear model. J. Amer. Statist. Assoc. 79, 406-414.
Robbins, H., 1951. Asymptotically subminimax solutions of compound statistical
decision problems. In Proc. Second Berkeley Symp. Math. Statist. Probab. 1.
University of California Press, Berkeley.
Robbins, H., 1955. An empirical Bayes approach to statistics. In Proc. Third Berkeley
Symp. Math. Statist. Probab.l, 157-164. University of California Press, Berkeley.
Robbins, H., 1964. The empirical Bayes approach to statistical decision problems.
Robbins, H., 1983. Some thoughts on empirical Bayes estimation. Ann. Statist. 1,
713-723. .
Roberts, H. Y., 1965. Probabilistic prediction. 1. Amer. Statist. Assoc. 60, 50-62.
Roberts, H. Y., 1967. Informative stopping rules and inference about population
size. 1. Amer. Statist. Assoc. 62, 763-775.
Robinson, G. K., 1979a. Conditional properties of statistical procedures. Ann. Statist.
7,742-755.
Robinson, G. K., 1979b. Conditional properties of statistical procedures for location
and scale parameters. Ann. Statist. 7, 756-771.
Rosenkrantz, R. D., 1977. Inference, Method, and Decision: Towards a Bayesian
Philosophy of Science. Reidel, Boston.
Rubin, D. B., 1984. Bayesianly justifiable and relevant frequency calculations for
the applied statistician. Ann. Statist. 12, 1151-1172.
Rubin, H., 1951. A complete class of decision procedures for distributions with
monotone likelihood ratio. Technical Report 9, Department of Statistics,
Stanford University, Stanford, California.
Rubin, H., 1971. A decision-theoretic approach to the problem of testing a null
hypothesis. In Statistical Decision Theory and Related Topics, S. S. Gupta and
J. Yackel (Eds.). Academic Press, New York.
Rubin, H., 1974. Decision-theoretic approach to some multivariate problems. In
Multivariate Analysis II, P. R. Krishnaiah (Ed.). Academic Press, New York.
Rubin, H., 1976. Some fast methods of generating random variables with preassigned
distributions I. General acceptance-rejection procedures. Mimeograph Series
#467, Department of Statistics, Purdue University, West Lafayette.
Rubin, H., 1977. Robust Bayesian estimation. In Statistical Decision Theory and
Related Topics II, S. S. Gupta and D. S. Moore (Eds.). Academic Press, New
York.
Rubin, H., 1987. A weak system of axioms for "rational" behavior and the non-
separability of utility from prior. Statist. Decisions S, 47-58.
Rubinstein, R. Y., 1981. Simulation and the Monte Carlo Method. Wiley, New York.
Rukhin, A. L., 1978. Universal Bayes estimators. Ann. Statist. 6, 345-351.
Rukhin, A. L., 1983. A class of minimax estimators of a normal quantile. Statist.
Probab. Letters 1,217-222.
Rukhin, A. L., 1984a. Universal estimators of a vector parameter. 1. Multivariate
Anal. 14, 135-154.
Rukhin, A. L., 1985. Estimating a ratio of normal parameters. Ann. Statist. 13,
1616-1624.
Rukhin, A. L., 1986. Admissibility and minimaxity results in estimation of exponen-
tial quantiles. Ann. Statist. 14, 220-231.
Bibliography 593
Rukhin, A. L., 1987. Estimation of a linear function ofthe normal mean and variance.
Sankhyii 49, 72-77.
Rukhin, A. L., and Strawderman, W. E., 1982. Estimating a quantile of an exponential
distribution. J. Amer. Statist. Assoc. 77, 159-162.
Rummel, F., 1983. Iterative berechnung von gamma-minimaxschatzverfahren.
Dissertation, Technischen Hochschule Darmstadt, Darmstadt.
Sacks, J., 1963. Generalized Bayes solutions in estimation problems. Ann. Math.
Statist. 34, 751-768.
Savage, L. J., 1954. The Foundations of Statistics. Wiley, New York.
Savage, L. J., 1961. The subjective basis of statistical practice. Technical Report,
Department of Statistics, University of Michigan, Ann Arbor.
Savage, L. J. et aI., 1962. The Foundations of Statistical Inference. Methuen,
London.
Savage, L. J., 1971. Elicitation of personal probabilities and expectations. J. Amer.
Schacter, R. D., 1984. Automating probabilistic inference. Technical Report, Depart-
ment of Engineering-Economic Systems, Stanford University, Stanford,
California.
Schervish, M. J., 1983. Combining expert judgements. Technical Report No. 294,
Department of Statistics, Carnegie-MeHon University, Pittsburgh.
Schwarz, G., 1962. Asymptotic shapes of Bayes sequential testing regions. Ann.
Schwarz, G., 1968. Asymptotic shapes for sequential testing of truncation parameters.
Sclove, S. L., 1968. Improved estimators for coefficients in linear regression. J. Amer.
Sen, P. K., and Saleh, A. K. Md. E., 1985. On some shrinkage estimators of
multivariate location. Ann. Statist. 13, 272-281.
Shafer, G., 1976. A Mathematical Theory of Evidence. Princeton University Press,
Princeton.
Shafer, G., 1981. Constructive probability. Synthese 48, 1-60.
Shafer, G., 1982a. Belief functions and parametric models (with discussion). J. Roy.
Shafer, G., 1982b. Constructive decision theory. Technical Report, Department of
Mathematics, University of Kansas, Lawrence.
Shafer, G., 1982c. Lindley'S paradox. J. Amer. Statist. Assoc. 77, 325-351.
Shapiro, c., and Wardrop, R., 1980. Bayesian sequential estimation for one-
parameter exponential families. J. Amer. Statist. Assoc. 75, 984-988.
Shinozaki, N., 1980. Estimation of a multivariate normal mean with a class of
quadratic loss functions. 1. Amer. Statist. Assoc. 75, 973-976.
Shinozaki, N., 1984. Simultaneous estimation of location parameters under quadratic
loss. Ann. Statist. 12, 322-335.
Shubik, M., 1982. Game Theory and the Social Sciences: Concepts and Solutions. MIT
Press, Cambridge, Massachusetts.
Siegmund, D., 1985. Sequential Analysis: Tests and Confidence Intervals. Springer-
Verlag, New York.
Simon, G., 1976. Computer simulation swindles with applications to estimates of
location and dispersion. Appl. Statist. 25, 266-274.
Smith, A. F. M., 1973a. Bayes estimates in the one-way and two-way models.
Smith, A. F. M., 1973b. A general Bayesian linear model. J. Roy. Statist. Soc. (Ser.
B) 35,67-75.
Smith, A. F. M., 1978. In discussion of Tanner, J. c., "Long-term forecasting
of vehicle ownership and road traffic." 1. Roy. Statist. Soc. (Ser. A) 141, 50-
51.
594 Bibliography
Smith, A. F. M., 1983. Bayesian approaches to outliers and robustness. In Specifying

Statistical.Models, J. F. Florens et al. (Eds.). Springer-Verlag, New York.
Smith, A. F. M., 1984. Present position and potential developments: some personal
views Bayesian statistics. J. Roy. Statist. Soc. (Ser. A) 147, 245-259.
Smith, A. F. M., and Spiegel halter, D. J., 1980. Bayes factors and choice criteria
for linear models. 1. Roy. Statist. Soc. (Ser. B) 42, 213-220.
Smith, C. A. B., 1961. Consistency in statistical inference and decision. J. Roy.
Smith, C. A. 8., 1965. Personal probability and statistical analysis. J. Roy. Statist.
Soc. (Ser. A) 128, 469-499.
Smith G., and Campbell, F., 1980. A critique of some ridge regression methods
(with discussion). 1. Amer. Statist. Assoc. 75, 74-103.
Sobel, M., 1953. An essentially complete class of decision functions for certain
standard sequential problems. Ann. Math. Statist. 24, 319-337.
Solomon, D. L., 1972. Gamma-minimax estimation of a multivariate location
parameter. 1. Amer. Statist. Assoc. 67, 641-646.
Spiegel halter, D. J., and Knill-Jones, R., 1984. Statistical and knowledge-based
approaches to clinical decision support systems, with an application in gastro-
enterology. J. Roy. Statist. Soc. (Ser. A) 147, 35-77.
Spruill, M. C., 1982. Admissibility of the natural estimator of the mean of a Gaussian
process. J. Multivariate Anal. 12, 568-574.
Srinivasan, c., 1981. Admissible generalized Bayes estimators and exterior boundary
value problems. Sankhya (Ser. A) 43, 1-25.
Srinivasan, c., 1982. A relation between normal and exponential families through
admissibility. Sankhya 44, 423-435.
Srinivasan, C., 1984a. A sharp necessary and sufficient condition for inadmissibility
of estimators in a control problem. Ann. Statist. 12, 927-944.
Srinivasan, c., 1984b. On admissible linear estimators in exponential families.
Technical Report, University of Kentucky, Lexington.
Steele, J. M., and Zidek, J. V., 1980. Optimal strategies for second guessers. J. Amer.
Stein, c., 1946. A note on cumulative sums. Ann. Math. Statist. 17,498-499.
Stein, C., 1955a. Inadmissibility of the usual estimator for the mean of a multivariate
normal distribution. In Proc. Third Berkeley Symp. Math. Statist. Probab. 1,
197-206. University of California Press, Berkeley.
Stein, C., 1955b. A necessary and sufficient condition for admissibility. Ann. Math.
Statist. 26, 518-522.
Stein, C., 1959. The admissibility of Pitman's estimator of a single location parameter.
Stein, c., 1962. A remark on the likelihood principle. J. Roy. Statist. Soc. (Ser. A)
125, 565-568.
Stein, c., 1965. Approximation of improper prior measures by prior probability
measures. In Bernouilli-Bayes-Laplace Festschrift, 217-240. Springer-Verlag,
New York.
Stein, C., 1966. An approach to the recovery of inter-block information in balanced
incomplete block designs. In Festschrift for 1. Neyman, F. N. David (Ed.).
Wiley, New York.
Stein, C., 1973. Estimation of the mean of a multivariate distribution. In Proceedings
of the Prague Symposium on Asymptotic Statistics.
Stein, C., 1975. Estimation of a covariance matrix. Reitz Lecture, IMS·ASA Annual
Meeting (and unpublished lecture notes).
Stein, C., 1981. Estimation of the mean of a multivariate normal distribution. Ann.
Statist. 9, 1135-1151.
Bibliography 595
Stein, M. L., 1984. An efficient method of sampling for statistical circuit design.
Technical Report, Mathematical Sciences Department, IBM T. J. Watson
Research Center, Yorktown Heights.
Stewart, L., 1979. Multiparameter univariate Bayesian analysis. J. Amer. Statist.
Assoc. 74, 684-693.
Stewart, L., 1983. Bayesian analysis using Monte Carlo integration-a powerful
methodology for handling some difficult problems. The Statistician 32, 195-200.
Stewart, L., and Johnson, J. D., 1972. Determining optimum bum-in and replacement
times using Bayesian decision theory. IEEE Transactions on Reliability R-21,
170-175.
Stigler, S., 1982. Thomas Bayes' Bayesian inference. J. Roy. Statist. Soc. (Ser. A)
145, 250-258.
Stijnen, Th., 1980. On the asymptotic behavior of monotonized empirical Bayes
rules. Doctoral Thesis. University of Utrecht, The Netherlands.
Stijnen, Th., 1982. A monotone empirical Bayes estimator and test for the one-
parameter continuous exponential family based on spacings. Scand. 1. Statist.
9, 153-158.
Stone, M., 1963. Robustness of nonideal decision procedures. J. Amer. Statist. Assoc.
58, 480-486.
Stone, M., 1970. Necessary and sufficient conditions for convergence in probability
to invariant posterior distributions. Ann. Math. Statist. 41, 1349-1353.
Stone, M., 1971. Strong inconsistency from uniform priors-with comments. 1. Amer.
Stone, M., 1979. Review and analysis of some inconsistencies related to improper
priors and finite additivity. In Proceedings of Sixth International Congress on
Logic, Methodology, and Philosophy of Science, L. J. Cohen, J. Los, H. Pfeiffer,
and K. P. Podewski (Eds.). North-Holland, Amsterdam.
Strawderman, W. E., 1971. Proper Bayes minimax estimators of the multivariate
normal mean. Ann. Math. Statist. 42, 385-388.
Strawderman, W. E., 1974. Minimax estimation of location parameters for certain
spherically symmetric distributions. 1. Multivariate Anal. 4, 255-264.
Strawderman, W. E., 1978. Minimax adaptive generalized ridge regression estimators.
Strawderman, W. E., and Cohen, A., 1971. Admissibility of estimators of the mean
vector of a multivariate normal distribution with quadratic loss. Ann. Math.
Statist. 42, 270-296.
Strenio, J. F., Weisberg, H. I., and Bryk, A. S., 1983. Empirical Bayes estimation of
individual growth-curve parameters and their relationship to covariates.
Biometrics 39, 71-86.
Susaria, V., 1982. Empirical Bayes theory. In Encyclopedia of Statistical Sciences,
Vol. 2, S. Kotz and N. Johnson (Eds.). Wiley, New York.
Takada, Y., 1979. A family of minimax estimators in some multiple regression
problems. Ann. Statist. 7, 1144-1147.
Thisted, R. A., 1982. Decision-theoretic regression diagnostics. In Statistical Decision
Theory and Related Topics III, S. S. Gupta and J. Berger (Eds.). Academic
Press, New York.
Thomas, L. c., 1984. Games, Theory and Applications. Wiley, New York.
Tiao, G. C., and Tan, W. Y., 1965. Bayesian analysis of random-effects models in
the analysis of variance. I. Posterior distribution of variance components.
Tiao, G. c., and Tan, W. Y., 1966. Bayesian analysis of random-effects models in
the analysis of variance. II. Effects of auto correlated errors. Biometrika 53,
477-495.
596 Bibliography
Tiao, G. C., and Zellner, A., 1964a. On the Bayesian estimation of multivariate
regression. J. Roy. Statist. Soc. (Ser. B) 26, 277-285.
Tiao, G. c., and Zellner, A., 1964b. Bayes theorem and the use of prior knowledge
in regression analysis. Biometrika 51, 219-230.
Tierney, L., and Kadane, J. B., 1986. Accurate approximations for posterior moments
and marginals. J. Amer. Statist. Assoc. 81, 82-86.
Tjur, T., 1978. Statistical inference under the likelihood principle. Preprint 1, Institute
of Mathematical Statistics, University of Copenhagen, Copenhagen.
Tsui, K. W., 1979. Multiparameter estimation of discrete exponential distributions.
Can. J. Statist. 7, 193-200.
Tsui, K. W., and Press, S. J., 1982. Simultaneous estimation of several Poisson
parameters under k-normalized squared-error loss. Ann. Statist. 10,93-100.
van Der Merwe, A. J., Groenewald, P. C. N., Nell, D. G., and van Der Merwe, C.
A., 1981. Confidence intervals for a multivariate normal mean in the case of
empirical Bayes estimation using Pearson curves and normal approximations.
Technical Report 70, Department of Mathematical Statistics, University of the
Orange Free State, Bloemfontein.
van Dijk, H. K., and Kloeck, T., 1980. Further experience in Bayesian analysis using
Monte Carlo integration. 1. Econometrics 14,307-328.
van Dijk, H. K., and Kloeck, T., 1984. Experiments with some alternatives for simple
importance sampling in Monte Carlo integration. In Bayesian Statistics II,
J. M. Bernardo, M. H. DeGroot, D. V. Lindley, and A. F. M. Smith (Eds.).
van Houwelingen, J. C., 1976. Monotone empirical Bayes tests for the continuous
one-parameter exponential family. Ann. Statist. 4, 981-989.
van Houwelingen, 1. c., 1977. Monotonizing empirical Bayes estimators for a class
of discrete distributions with monotone likelihood ratio. Statistica Neerlandica
31,95-104.
van Houwelingen, J. C., and Stijnen, Th., 1983. Monotone empirical Bayes estimators
for the continuous one-parameter exponential family. Statistica Neerlandica 37,
29-43.
van Houwelingen, J. C., and Verbeek, A., 1980. On the construction of monotone
symmetric decision rules for distributions with monotone likelihood ratio.
Preprint 149, Department of Mathematics, University of Utrecht, The Nether-
lands.
Vardeman, S., and Meeden, G., 1984. Admissible estimators for the total of a
stratified population that employ prior information. Ann. Statist. 12, 675-684.
Vardi, Y., 1979. Asymptotic optimality of certain sequential estimators. Ann. Statist.
7, 1034-1039.
Villegas, C., 1977. On the representation of ignorance. J. Amer. Statist. Assoc. 72,
651-654.
Villegas, C., 1981. Inner statistical inference, II. Ann. Statist. 9, 768-776.
Villegas, C., 1984. On a group structural approach to Bayesian inference. Technical
Report 84-11, Department of Mathematics, Simon Fraser University, Burnaby.
Vinod, H. D., and Ullah, A., 1981. Recent Advances In Regression Methods. Marcel
Dekker, New York.
Von Neumann, J., 1928. Zur theorie der gesellschaftspiele. Math. Annalen 100,
295-320.
Von Neumann, J., and Morgenstern, 0., 1944. Theory of Games and Economic
Behavior (3rd edn. 1953). Princeton University Press, Princeton, NJ.
Wagner, C., 1982. Allocation, Lehrer models, and the consensus of probabilities.
Theory and Decision 14,207-220.
Wald, A., 1947. Sequential Analysis. Wiley, New York.
Wald, A., 1950. Statistical Decision Functions. Wiley, New York.
Bibliography 597
Wald, A., and Wolfowitz, J., 1948. Optimum character of the sequential probability
ratio test. Ann. Math. Statist. 19, 326-339.
Walker, A. M., 1969. On the asymptoti:: behavior of posterior distributions. 1. Roy.
Wallace, D. L., 1959. Conditional confidence level properties. Ann. Math. Statist.
30, 864-876.
Weerahandi, S., and Zidek, J. V., 1981. Multi-Bayesian statistical decision theory.
1. Roy. Statist. Soc. (Ser. A) 144, 85-93.
Weerahandi, S., and Zidek, J. V., 1983. Elements of multi-Bayesian decision theory.
Ann. Statist. 11, 1032-1046.
Weiss, L., 1961. Statistical Decision Theory. McGraw-Hill, New York.
Whitney, A. W., 1918. The theory of experience rating. Proceedings of the Casualty
Actuarial Society 4, 274-292.
Whittle, P., 1982. Optimisation over Time: Dynamic Programming and Stochastic
Control, Vol. 1. Wiley, New York.
Widder, D. V., 1946. The Laplace Transform. Princeton University Press, Princeton,
NJ.
Williams, J. D., 1954. The Compleat Strategyst. McGraw-Hill, New York.
Winkler, R. L., 1967a. The quantification of judgement: some methodological
suggestions. 1. Amer. Statist. Assoc. 62, 1105-1120.
Winkler, R. L., 1967b. The assessment of prior distributions in Bayesian analysis.
Winkler, R. L., 1968. The consensus of subjective probability distributions. Manage.
Sci. 15, B61-B75.
Winkler, R. L., 1972. Introduction to Bayesian Inference and Decision. Holt, Rinehart,
and Winston, New York.
Winkler, R. L., 1980. Prior information, predictive distributions, and Bayesian
model-building. In Bayesian Analysis in Econometrics and Statistics, A. Zellner
Winkler, R. L., 1981. Combining probability distributions from dependent informa-
tion sources. Manage. Sci. 27, 479-488.
Wolfenson, M. and Fine, T. L., 1982. Bayes-like decision making with upper and
lower probabilities. 1. Amer. Statist. Assoc. 77, 80-88.
Woodroofe, M., 1976. Frequentist properties of Bayesian sequential tests. Biometrika
63, 101-110.
Woodroofe, M., 1978. Large deviations oflikelihood ratio statistics with applications
to sequential testing. Ann. Statist. 6, 72-84.
Woodroofe, M., 1980. On the Bayes risk incurred by using asymptotic shapes.
Commun. Statist.-Theory and Methods 9, 1727-1748.
Woodroofe, M., 1981. A.P.O. rules are asymptotically nondeficient for estimation
with squared-error loss. Z. Wahrsch. verw. Gebiete 58, 331-341.
Woodroofe, M., 1982. Empirical Bayes estimation of the mean of normal distribution
with convex loss. In Statistical Decision Theory and Related Topics III, S. S.
Gupta and J. Berger (Eds.). Academic Press, New York.
Zacks, S., 1971. The Theory of Statistical Inference. Wiley, New York.
Zaman, A., 1981. A complete class theorem for the control problem, and further
results on admissibility and inadmissibility. Ann. Statist. 9, 812-821.
Zellner, A., 1971. An Introduction to Bayesian Inference in Econometrics. Wiley, New
York.
Zellner, A., 1977. Maximal data information prior distributions. In New Methods
in the Applications of Bayesian Methods, A. Aykac and C. Brumat (Eds.).
Zellner, A., 1984a. Posterior odds ratios for regression hypotheses: general consider-
ations and some specific results. In Basic Issues in Econometrics. University of
Chicago Press, Chicago.
598 Bibliography
Zellner, A., 1984b. Basic Issues in Econometrics. University of Chicago Press, Chicago.
Zellner, A., and Highfield, R. A., 1988. Calculation of maximum entropy distributions
and approximation of marginal posterior distributions. J. Econometrics 37,
195-209.
Zellner, A., and Siow, A., 1980. Posterior odds ratios for selected regression
hypotheses. In Bayesian Statistics, J. M. Bernardo, M. H. DeGroot, D. V.
Lindley, and A. F. M. Smith (Eds.). University Press, Valencia.
Zeytinoglu, M., and Mintz, M., 1984. Optimal fixed size confidence procedures for
a restricted parameter space. Ann. Statist. 12, 945-957.
Zheng, Z., 1982. A class of generalized Bayes minimax estimators. In Statistical
Decision Theory and Related Topics III, S. S. Gupta and J. Berger (Eds.).
Zidek, J., 1969. A representation of Bayes invariant procedures in terms of Haar
measure. Ann. Inst. Statist. Math. 21, 291-308.
Zidek, J., 1970. Sufficient conditions for the admissibility under squared-error loss
of formal Bayes estimators. Ann. Math. Statist. 41, 446-456.
Zidek, J., 1971. Inadmissibility of a class of estimators of a normal quantile. Ann.
Math. Statist. 42, 1444-1447.
Zidek, J., 1976. A necessary condition for the admissibility under convex loss of
equivariant estimators. Technical Report No. 113, Stanford University,
Stanford, California.
Zidek, J., 1978. Deriving unbiased risk estimators of multinormal mean and
regression coefficient estimators using zonal polynomials. Ann. Statist. 6, 769-
782.
Zidek, J., 1986. Multi-Bayesian estimation theory. Statist. Decisions 4, 1-18.
Notation and Abbreviations
The symbols listed here are those used throughout the book. Symbols specific
to a given chapter are, for the most part, not listed. This glossary is for
reference only, in that virtually all symbols are also explained when first
used in the book. A page number after an entry indicates where in the book
a more extensive explanation can be found.
Mathematical Notation
R\ R2, RP: the line, the plane, p-dimensional Euclidean space.
y, A: bold-faced letters are column vectors or matrices. The (i,j)th element
of a matrix A will be denoted A ij•
y', A': the "t" denotes transpose.
A-I, det A, tr A: the inverse, determinant, and trace of a matrix A.
Ip: the (p x p) identity matrix.
1,0: the vectors of all ones and zeros, respectively.
Iyl: the Euclidean norm of yE RP (absolute value if y ERI). Thus
Iy\
=(L:=I y;)1/2.
(a, b), [a, b], (a, b], [a, b): the open interval from a to b, the closed interval,
and half-open intervals.
{a, b}: the set consisting of the elements a and b.
B C, B:
the complement and closure of the set B.
IB(Y): the indicator function on the set B (equals one if Y E B and zero
otherwise).
g'(y), g"(y): the first and second derivatives of the function g.
600 Notation and Abbreviations
log y: the logarithm of y to the base e.

min, max, inf, sup, lim: minimum, maximum, infimum, supremum, and limit.
('), u: intersection, union.
=:: approximately equal to.
xy: the line segment (in RP) joining the points x and y.
Xn ~ Xc: the sequence of points {xn} converges to Xc, i.e.,
lim IXn -
n-+oo
xol = O.
#: the number of.
f( a ): the gamma function.
(;): defined as n!j[x!(n-x)!].
Probabilistic Notation
x, ~ x: the random variable X, the sample space, a realization of X (p.3).

0, e: a parameter (or "state of nature"), the parameter space (p.3).
f(xIO), F(xIO): the density of X given 0, the cumulative distribution function
of X given 0 (p. 4).
Jh(x) dF(xIO): see page 4.
P(A) or P(X E A): the probability of the set A (p. 3).
E[h(X)]: the expectation of h(x) (p. 4).
Subscript on P or E (such as E9): a parameter value under which the
probability or expectation is to be taken (p. 4).
Superscript on P, E, or F (such as EX): clarifies the relevant random
variable or distribution (p. 4).
z(a): the a-fractile of the distribution of the random variable X (pp. 79,
162).
(a), (8)(x, A): "( )" is a notational device used to denote the probability
distribution which selects the enclosed quantity with probability one.
Thus (8)(x, A) = I A (8(x».
~9S: entropy (p. 91).
Statistical Notation
H o, HI: null hypothesis, alternative hypothesis.

cfJ(x): a test function; i.e., cfJ(x) is the probability of rejecting the null
hypothesis (zero or one for a nonrandomized text) when x is observed.
Notation and Abbreviations 601
f3</>( 0) or f3( 0): the power function of a test; i.e., the probability of rejecting
the null hypothesis when 0 is the parameter value.
ao( <p) or ao, a I (<p) or a I: the probabilities of Type I and Type II errors,
respectively, for testing Ho: 0 = 00 versus HI: 0 = 01 • Thus ao = f3( ( 0 )
and a l = 1- f3( ( 1 ).
i: the sample mean; i.e., i = lin L~=I Xi.
1(0): the likelihood function (i.e., 1(0) =/(xIO» (p. 27).
17"( 0): the prior density for 0 (pp. 3, 4).
m(xl17") or m(x): the marginal density of X (p. 95).
17"(Olx): the posterior distribution of 0 given X (p. 126).
IL"'(X), V"'(x): posterior mean and variance (p. 136).
C or C(x): a confidence or credible set for 0 (pp. 140,414).
J( 0): expected Fisher information (pp. 88, 224).
i(x): observed (or conditional) Fisher information (p. 224).
Decision Theoretic Notation

a, d: action, action space (p. 3).
L( 0, a): the loss function (pp. 3, 59).
~: reward space (p. 47).
U(r) or U(O, a): utility function (pp. 47,58).
p( 17"*, a): the Bayesian expected loss of a with respect to 17"* (p. 8), or
posterior expected loss when 17"* is the posterior distribution (p. 159).
a"'o: a Bayes action (p. 16).
~, ~*: nonrandomized decision rule (p. 9), randomized decision rule (p. 12).
L(O, ~*): the loss function for a randomized decision rule (p. 13).
R(O,~) and R(O, ~*): the risk function (expected loss) of a decision rule
(pp. 9 and 14).
~: the class of nonrandomized decision rules with R(O, 15)<00 for all 0
(p.11).
~*: the class of randomized decision rules with R( 0, 15*) < 00 for all 0
(p.14).
r( 17",15) and r( 17", 15*): the Bayes risk of a decision rule (p. 11).
15"': a Bayes decision rule (p. 17).
r( 17"): the Bayes risk of 17" (i.e., r( 17") = r( 17", 15"'» (p. 17).
rr(c5): f-Bayes risk of 15 (p. 213).
Author Index
Aitchison, J. 67, 158, 169 168, 169, 178, 183, 195, 197-199,
Aitkin, M. 26 203,205-207,211,215,217, 220,
Akaike, H. 89 221, 226-228, 233, 237, 240, 242-
Alam, K. 369 244,247,258,266,268,361-370,
Albert, J. H. 169, 218 503, 506, 509, 510, 542, 543, 549,
Allais, M. 50 550, 552, 554
Alpert, M. 82 Berger, R. 217,278
Alvo, M. 481 Berk, R. H. 545
Amster, S. J. 457 Berkson, J. 22
Anscombe, F. J. 228, 503 Berliner, L. M. 98, 99, 169, 178, 203,
Antoniak, C. E. 107, 183 205,207,211,213,215,217,221,
Armitage, P. 507 233, 364, 369, 554
Arnold, S. F. 369 Bermudez, J. D. 277
Arrow, K. J. 281, 444 Bernardo, J. M. 66,89,90,94, 110,
Atchison, T. A. 169 231, 277
Berry, D. 107, 183, 435, 481
Bacharach, M. 281 Bhattacharya, P. K. 366
Bahadur, R. R. 489, 506 Bibby, J. 369
Balder, E. J. 523, 537 Bickel, P. J. 217,221,222,353,477,
Baranchik, A. J. 369 479,480
Barlow, R. E. 277, 510 Birnbaum, A. 23,31,32,37,503,539
Barnard, G. A. 26,31,503 Bishop, Y. 169, 183
Barndorff-Nielsen, O. 572 Blackwell, D. 41, 260, 327, 346, 355,
Barnett, V. 26, 76 379,380,384,422,444
Bartholomew, D. J. 503 Blum, J. R. 215
Basu, D. 31,32,33, 503, 507 Blyth, C. R. 547, 548
Bayes, T. 3, 89, 96, 116, 129 Bock, M. E. 369
Bechhofer, R. E. 541 Bondar, J. V. 259,420
Becker, G. M. 53 Bordley, R. F. 277
Berger, J. 15,24,26,27, 29, 31-33, Borel, E. 310
35,37,66,90,98,99,110,113, Box, G. E. P. 35, 89, 110, 119, 124,
120, 124, 126, 148, 151-154, 156, 133, 183, 201, 203, 249
604 Author Index
Boyer, J. E., Jr. 169 De Robertis, L. 197,205, 206

Brandwein, A. 361 de Waal, D. 280,281
Brier, G. W. 66 Dey, D. K. 243, 244, 361, 369
Brockett, P. L. 94, 232 Diaconis, P. 106, 132, 159,229,277,
Brown, L. D. 26, 159, 221, 251, 346, 283, 346, 361, 537, 546
350, 360, 369, 370, 423, 500, 534, Diamond, G. A. 120, 151
535, 537, 540-543, 545-547, 549, Dickey, J. M. 76, 96, 148, 151, 152,
550, 552-554 183,206,228,246,267,268,277,
Brown, P. J. 369 284
Brown, R. V. 198,277 Donovan, T. M. 217
Bryk, A. S. 169 DuMouchel, W. M. 183
Buehler, R. J. 259-261,413 Dunsmore, I. R. 67, 158
Bunke, O. 361 Dvoretsky, A. 523
Campbell, F. 364 Eaton, M. L. 66,261,391, 539

Caridi, F. 542 Eberl, W., Jr. 580
Casella, G. 172,353,369 Eddy, W. F. 203,249
Casti, J. L. 435 Edwards, A. W. F. 26,31
Chaloner, K. 432 Edwards, W. 81, 119, 124, 152, 153,
Charnes, A. 94, 232 223, 503, 504
Chen, C. F. 183 Efron, B. 169, 178, 219, 221, 244, 361,
Chen, S. Y. 221, 361-363, 365, 367, 365,369
368 Ellsberg, D. 122
Cheng, P. 361, 550 Ewing, G. M. 92
Chernoff, H. 435,481
Chong-Hong, C. 284
Chou,J. P. 361,363,370 Faith, R. E. 361
Chow, Y. S. 435 Farrell, R. H. 422, 537, 539, 543, 546,
Christensen, R. 107, 183 547, 549, 550
Chuang, D. T. 206,251 Ferguson, T. S. 65, 121, 346, 383, 499,
Clevenson, M. 360, 370 545
Cohen, A. 68, 500, 534, 535, 540, 541, Fienberg, S. 169, 183
543,545, 549 Fine, T. 199,286
Cole, N. S. 183 Fishburn, P. C. 50, 121, 206
Coleman, A. 314 Fisher, R. A. 26,31,35, 88, 388
Copas, J. B. 169 Forrester, J. S. 120, 151
Cornfield, J. 577 Fox, M. 423, 550
Cox, D. R. 23, 25 Fraser, D. A. S. 26,251,260,261,388
Cressie, N. 104, 169 Freedman, D. A. 106,259
Freeman, P. R. 268
French, S. G. 275,277,281
Dalal, S. R. 132 Fristedt, B. 435
Das Gupta, A. 151,156,228,247,
266, 268, 361, 370, 550
Dawid, A. P. 89, 106, 228 Gardenfors, P. 199
Deely, J. J. 183, 195, 217 Gatsonis, C. A. 66, 261
de Finetti, B. 66, 75, 76, 106, 119, Gaver, D. P. 232
121, 283 Geertsema, J. C. 581
DeGroot, M. H. 50, 53, 71, 75, 108, Geisser, S. 89,90, 158,203,249
148, 183, 225, 278, 287, 292, 435, Genest, C. 277,281
474 George, E. I. 369
Dempster, A. P. 100, 148, 153, 169, Ghia, G. D. 539
195,203,249,252,277 Ghosh, B. K. 435, 495
Author Index 605
Ghosh, J. K. 225 Hui, S. 168, 169

Ghosh, M. 361, 370, 543, 550 Huzurbazar, V. S. 35
Gilliland, D. C. 169, 537 Hwang, J. T. 172,251,361, 363, 369,
Giron, F. J. 199 370, 549, 550, 554
Girshick, M. A. 327,346,355,379, Hylland, A. 281
380, 384, 444
Gitting, J. C. 435
Gieser, L. J. 369 Ighodaro, A. 543
Goel, P. K. 108, 183 Isaacs, H. H. 206
Goldstein, M. 197, 284 Isaacson, D. 228
Good, I. J. 34, 35, 66, 76, 80, 94, 99, Isii, K. 537
106, 110, 113, 119, 148, 156, 168,
183, 195, 198, 199, 203, 206, 215, Jackson, D. A. 217
249, 252, 284 Jackson, P. H. 183
Govindarajulu, Z. 435 James, W. 256, 361, 364, 422, 543, 549
Groenewald, P. C. N. 182,280,281 Jaynes, E. T. 35, 83, 89, 90, 91, 92, 94,
Gupta, A. K. 571 110, 119
Gupta, S. S. 68, 217, 541 Jeffrey, R. 9,277,283
Gutmann, S. 361 Jeffreys, H. 29,35, 76, 83, 87, 88, 89,
90, 110, 119, 133, 151, 153, 156,
Haff, L. R. 160,169,178,361,365, 203, 225, 249, 270
369 Jenkins, G. M. 503
Hagen, O. 50 Jennrich, R. I. 100
Hald, A. 350 Jewell, W. S. 132, 136, 169
Hall, W. J. 89, 132 Johnson, J. D. 265
Halmos, P. R. 408 Johnson, R. A. 225
Hammersley, J. M. 265 Johnson, R. W. 361
Handscomb, D. C. 265 Johnstone, I. M. 225, 265, 553, 554
Harris, 1. E. 183 Jones, A. J. 281,314
Hartigan, J. A. 83, 87, 197,205,206, Joshi, S. N. 225
225 Joshi, V. M. 550
Hawkes, J. S. 369 Judge, G. 369
Heath, D. 258, 259
Heyde, C. C. 225 Kadane,J. B. 76,96,206,251,266
Highfield, R. A. 94 Kahneman, D. 76, 82, 106, 198
Hildreth, C. 268 Karlin, S. 530, 532, 533, 535, 538, 550
Hill, B. 90, 135, 148, 177, 183, 195, Keener, R. W. 435
206, 223, 228, 252, 258, 261 Keeney, R. L. 53, 57,68
Hinde, J. 26 Kelley, T. L. 168
Hinkley, D. V. 23, 67, 250 Kempthome, P. J. 353
Hirschmann, I. I. 544 Kiefer, J. 26,27,122,397,415,420,
Hoadley, B. 169 431,477,481,501,541
Hodges, J. L., Jr. 148,219,221 K1oeck, T. 265
Hoeffding, W. 469 Knill-Jones, R. 277
Hoffman, K. 550 Kozek, A. 537
Hogarth, R. M. 76, 81, 277, 281 Kraft, C. H. 286
Holland, P. 169, 183 Kudo, H. 215, 413
Hooper, P. M. 418 Kuo, L. 107, 183
Hora, R. B. 413 Kusama, T. 537
Howard, R. A. 277
Hsiao, P. 217
Huber, P. J. 69,207,248 Laird, N. M. 100, 101, 178
Hudson, H. M. 169, 361, 363, 364 Lalley, S. 553
606 Author Index
La Motte, L. R. 550 Mousa, A. 369

Lane, D. A. 90, 121, 259 Muirhead, R. J. 361
Laplace, P. S. 82,83,89, 187,225 Murphy, A. H. 206
Larson, R. E. 435
Lauritzen, S. L. 106
Leamer, E. E. 156,206,248 Nachbin, L. 408
Le Cam, L. 120, 122,225,346, :/37, Nash, J. F., Jr. 281
546 Naylor, J. C. 262
Lehmann, E. L. 37, 65, 68, 88, 144, Nell, D. G. 182
148, 219, 221, 353, 420 Nelson, W. 353
Lehn,J. 217 Neyman, J. 22, 23, 523-525
Lempers, F. B. 156 Noda, K. 537
Leonard, T. 100, 101, 169, 178, 183 Novick, M. R. 89, 106, 183, 251
Lepage, R. 495
Lin, P. E. 369
Lindley, D. V. 28, 66, 75, 106, 119,
O'Bryan, T. E. 169
121, 148, 151, 156, 183, 186, 195,
O'Hagan, A. 137,249
198,266,275,277,283,286,503
Olkin, I. 361
Lindman, H. 119, 124, 152, 153, 223,
Oman, S. D. 369
503, 504
Lindsay, B. G. 101, 178
Lord, F. M. 104, 169
Paick, K. H. 94, 232
Lorden, G. 481
Panchapakesan, S. 68
Louis, T. A. 100, 177
Patel, C. M. 100, 169
Luce, R. D. 281
Pearson, E. S. 22, 523-525
Lush, J. L. 168
Peng, J. C. M. 361, 363, 370
Peters, S. C. 76, 96
Phillips, L. D. 28, 503
Mackay, J. 251 Pilz, J. 432
Magwire, C. A. 469 Pitman, E. J. G. 399, 400
Mandelbaum, A. 550 Polasek, W. 206, 248
Marazzi, A. 217,221,222 Portnoy, S. 537
Marden, J. I. 539 Pratt, J. W. 30, 138, 148, 215, 252,
Maritz, J. S. 104, 169 286,503
Marschak, J. 53 Press, S. J. 183, 278, 361, 370
Martz, H. F. 169, 215 Proschan, F. 136
Matheson, J. E. 277 Purves, R. A. 159,259
Matthes, T. K. 539
McConway, K. J. 277
Meeden, G. 228, 543, 549, 550 Rabena, M. 231
Meinhold, R. J. 177 Raifia, H. 53, 57,68,82, 130, 151,
Menges, G. 215 160, 277, 281, 510
Mensing, R. W. 277 Ralescu, D. 550
Miescke, K. J. 541 Ralescu, S. 550
Milnes, P. 420 Ramsay, J. O. 251
Mintz, M. 353 Ramsey, F. P. 121
Moeschlin, O. 580 Rao, C. R. 41, 169, 172, 178,365, 550
Morgenstern, o. 310 Ray, S. N. 455
Morris, C. 168-170, 172, 174, 175, Reilly, A. 183
178, 183, 189, 194, 195,215,219, Reinsel, G. C. 172, 178,365
221, 244, 361, 365, 369 Rios, S. 199
Morris, P. A. 277 Robbins, H. 96, 168, 169, 178,215,
Moses, L. E. 577 435
Author Index 607
Roberts, H. V. 158, 510 Smith, G. 364

Robinson, G. K. 66, 259-261 Smith, W. S. 76, 96
Rosenblatt, 1. 215 Sobel, M. 540, 541
Rosenkrantz, R. D. 86,91 Solomon, D. L. 594
Roth, A. J. 100, 169 Spiegelhalter, D. 1. 156, 277
Rubin, D. B. 100, 124, 169, 203, 215, Spruill, M. C. 550
510 Srinivasan, C. 361, 542, 543, 550, 553,
Rubin, H. 21, 50,69, 121, 195,227, 554
228, 260, 265, 374, 460, 530, 532, Steele, 1. M. 594
533, 535 Stein, C. 66, 87, 159, 230, 244, 256,
Rubinstein, R. Y. 265 346,360, 361, 363, 364, 369, 413,
Rukhin, A. L. 206, 361, 549 418,420,422,487, 537, 543, 546,
Rummel, F. 217 547, 549, 552
Stein, M. L. 264
Stewart, L. 265
Sackrowitz, H. D. 68 Stigler, S. 96, 116
Sacks, 1. 477, 481, 542 Stijnen, Th. 169, 534, 537
Sahlin, N. E. 199 Stone, M. 89, 90, 260
Saleh, A. K. Md. E. 361 Strawderman, W. E. 221, 237, 240,
Sampson, P. F. 100 353, 361, 369, 534, 535, 540, 541,
Samuel-Cahn, E. 500, 541 543
Santner, T. 543 Strenio, 1. F. 169
Savage, L. 1. 2, 26, 76, 112, 119, 121, Sudderth, W. D. 121, 258, 259
124, 152, 153, 223, 281, 377, 503, Susarla, V. 169
504,507
Schacter, R. D. 277
Schervish, M. 1. 277
Takada, Y. 369
Schlaifer, R. 130, 151, 160, 510
Tan, W. Y. 183
Schnieper, R. 169
Thayer, D. T. 183
Schwarz, G. 481
Thisted, R. A. 369
Sc\ove, S. L. 369
Thomas, L. C. 310,314
Sedransk, N. 183
Tiao, G. C. 35, 89, 110, 119, 133, 183,
Seidenberg, A. 286
203, 228, 246, 249
Selliah, J. B. 361
Tierney, L. 266
Sellke, T. 148, 152-154, 156, 233
Tjur, T. 595
Selwyn, M. R. 100, 169
Toutenburg, H. 369
Sen, P. K. 361
Truax, D. R. 539
Shafer, G. 50, 59, 76, 148, 156, 277,
Tsao, H. J. 169
285,286
Tsui, K. W. 361,363, 370
Shapiro, C. 481
Tversky, A. 76, 82, 106, 198, 277
Shigemasu, K. 183
Shinozaki, N. 251, 361, 369
Shor, S. W. W. 510
Shubik, M. 314 Ullah, A. 369
Siegmund, D. 435, 500
Simon, G. 265
Singpurwalla, N. D. 136, 177, 277 van Der Merwe, A. J. 182
Sinha, B. K. 225, 550 van Der Merwe, C. A. 182
Siow, A. 148, 151, 153 van Dijk, H. K. 265
Slovic, P. 76, 82, 106, 198 van Houwelingen, 1. C. 534, 535, 537
Smiriga, N. G. 277 van Zyl, G. 280, 281
Smith, A. F. M. 106, 122, 124, 156, Vardeman, S. 549
183, 186, 249, 262, 268 Vardi, Y. 481
Smith, C. A. B. 121, 151, 199 Velleman, P. 265
608 Author Index
Verbeek, A. 535 Wolfenson, M. 199

Villegas, C. 83, 89 Wolfowitz, J. 499, 523
Vinod, H. D. 369 Wolpert, R. 15,26,29, 31, 32, 33, 35,
Von Neumann, J. 310 110, 120, 124, 126, 369, 503, 506,
509, 510
Woodroofe, M. 183, 481
Wagner, C. 281
Wald, A. 2, 434, 435, 444, 474, 481, Yahav,J. A. 477,479,480
486, 488, 492, 498, 499, 523, 537 Ylvisaker, D. 132, 229
Walker, A. M. 225
Wallace, D. L. 259
Waller, R. A. 169, 215 Zabell, S. 277, 283
Wardrop, R. 481 Zacks, S. 597
Weerahandi, S. 280,281 Zaman, A. 542, 554
Weisberg, H. I. 169 Zeckhauser, R. 281
Weiss, L. 597 Zellner, A. 35,89,90,94, 110, 133,
Whitney, A. W. 168 148, 151, 153, 183,228,246
Whittle, P. 435 Zeytinoglu, M. 353
Widder, D. V. 544 Zheng, Z. 369
Williams, J. D. 15, 330 Zidek, J. V. 89,277,280,281,360,
Winkler, R. L. 76, 96, 113, 277, 281 361, 369, 370, 413, 423, 550, 552
Winsten, C. B. 503 Zimmer, W. J. 217
Subject Index
Adaptive ridge regression estimators robustness of, see Robustness

557 sequential 444
Admissibility 10 Bayes factor 146, 150, 152
and complete classes 522 Bayesian calculation 262
and stopping rules 509 approximations 265
of Bayes rules 253 in hierarchical problems 192, 194,
of generalized Bayes rules 254 238, 242, 245, 247
of invariant rules 422 Monte Carlo integration 262
of lower boundary points 336 numerical integration 263
of minimax rules 371 of credible sets 142
of multivariate tests of a point null Bayesian communication 267, 282
hypothesis 539 Bayesian decision theory 158
of one-sided tests 530 choice of sample size 435
of sample mean in 1 or 2 classification problems 165, 357
dimensions 548, 549 estimation 161
ofSPRT 498 extensive form of 160
Stein's necessary and sufficient finite action problems 163
condition for 546 hypothesis testing 163
verification of 547 normal form of 160
in estimating normal means 552 robustness, see Robustness
in estimating Poisson means 553 with inference losses 166
Asymptotically pointwise optimal 477 Bayesian expected loss 8, see also
Posterior expected loss
Bayesian inference 132
Bayes decision rules 17, 159, see also and classical inference 119, 137,
Bayesian decision theory 406
admissibility and inadmissibility of credible sets 140, 143
253 decision-theoretic 166
complete class of 337, 523 estimation 133
limits of 537, 546, 547 hypothesis testing 145, 268
possible nonexistence Qf 382 Bayesian robustness, see Robustness
610 Subject Index
Bayes m-inner truncated procedure 460 for estimating Poisson means 553
as approximation to Bayes for estimation in the exponential
procedure 461 family 541
Bayes m-truncated procedure 449 for finite parameter space
as approximation to Bayes Bayes rules 337, 523
procedure 454, 455, 459, 461 lower boundary of the risk set
as exact Bayes procedure 454, 455 335, 523
for sequential sample 451 testing simple hypotheses 524
possible nonexistence of 459 for multivariate testing of a point
Bayes risk 11, 159 null hypothesis 539
concavity of 483 for one-sided sequential testing 540
of sequential procedures 445 for one-sided testing 527, 530
with sampling cost 435 generalized Bayes rules 541, 552,
Bayes risk principle 17 553
Bayes's theorem 129 limits of Bayes rules 537, 546, 547
Best invariant decision rule 397, 409 monotone decision rules 547
Binomial probability 562 nonrandomized decision rules 40,
conjugate prior for 287 523, 541
estimators of two-sided tests 538
invariant 394, 401 Compound decision theory 96, 172
minimax 353, 375 Concave function 39, 45
sequential Bayes 454, 457 Conditional Bayes principle 16
likelihood function for 28 Conditional perspective 24, 29, 33, 44,
noninformative prior for 89 124, 160, 214, 502, 506
testing simple hypotheses Confidence level 414
minimax 355 Confidence principle 23, 215
sequential Bayes 451, 456, 462 Confidence rules or sets 414, see also
SPRT 495, 518 Credible sets
Bounded from below 336, 355 invariant 414, 416, 417
lack of final precision 24
loss functions for 65
size of 41, 415, 416
Cauchy distribution 560 Conjugate prior, see Prior distribution
Bayesian inference 141 Convex combination 38
location parameter 83 Convex function 38, 39, 45
Censoring 30 Convex hull 38
Chi-square distribution 560 Convex set 38
confidence intervals 417 Credible sets 140
conjugate prior for 287 coincidence with confidence sets
Classification problems 165, 357 141, 414
Closed from below 336, 355 highest posterior density (HPD)
Coherency 120,259 140, 418
Colonel Blotto problem 15 lack of invariance of HPD 144
Combining evidence 272 loss functions for 167
decision-theoretic 277 multivariate 143, 189
Complete and essentially complete size of 140, 415, 430
classes 521 S-optimal 145, 291
admissible rules 522
Bayes rules 337, 523, 546
decision rules based on a sufficient
statistic 36, 522 Decision rule 9, 12
decision rules with continuous risk Bayes 17, 159
functions 545 Bayes sequential procedure 444
for estimating normal means 552 invariant 395
Subject Index 611
minimax 18 Equalizer decision rule 353

monotone 532, 535 Equalizer strategy 322,325, 337, 379
nonrandomized 9 Essentially complete classes 521, see
randomized 12 also Complete and essentially
sequential decision procedure 441 complete classes
Density Estimation 5, 9
beta 560 Bayes 133, 161
binomial 562, see also Binomial error 136
probability for absolute error loss 162
Cauchy 560, see also Cauchy for linear loss 162
distribution for quadratic loss 293
chi-square 560, see also Chi-square for squared-error loss 161
distribution in inference 133
Dirichlet 561 robustness of, see Robustness
exponential 560, see also best invariant 405
Exponential distribution for location parameter 398, 399,
exponential family 526, see also 405,427
Exponential family for scale parameter 400, 428
F (or Fisher) 560 empirical Bayes 167
gamma 560, see also Gamma for normal means 169, 173
distribution for Poisson means 178
geometric 562, see also Geometric hierarchical Bayes 180
distribution minimax 350, 353, 363, 369
inverse gamma 561 monotone 534
multinomial 562, see also sequential 466, 480
Multinomial distribution Exchangeability 104
multivariate normal 560, see also Exponential distribution 560
Multivariate normal mean conjugate prior for 287
multivariate t 561 in a classification problem 357
negative binomial 562, see also invariant estimation for 388, 394,
Negative binomial distribution 396
normal 559, see also Normal minimax test for 351
distribution and Normal Exponential family 526, 542
mean complete classes for 538, 539, 540,
t (or Student's t) 561, see also 542, 550
t-distribution monotone likelihood ratio of 526
uniform 560, see also Uniform Extended Bayes rules 354
distribution Extensive form of Bayes analysis 160
Dutch book arguments 259
Final precision, see Initial and final

Empirical Bayes methods 96, 167 precision
construction of prior 96, 167 Finite action (multiple decision)
for exchangeable normal means 169 problems 163, 325, 530
for general normal means 173 Bayes 163
for Poisson means 178 classification 165, 357
nonparametric empirical Bayes in game theory 325
(NPEB) 168, 178 monotone 530
parametric empirical Bayes (PEB) Fisher information 87
168, 169, 173 expected 87, 88, 224
use of monotonization 536 observed 224
Entropy 66,91,92, 104 Fixed sample size look ahead
e-minimax strategy 346 procedure 457,459,461
612 Subject Index
Formal Bayes rule 254 and invariance 410

admissibility and inadmissibility of and minimaxity 350
254 complete classes of 542
Fractiles 79, 162 identifying 543
Frequentist perspective 9, 22, 25, 26, Generalized maximum likelihood
27,29,33,44,213 estimator 133
and inadmissibility 257 Geometric distribution 562
Fundamental identity of sequential as maximum entropy distribution
analysis 489 92
Group decision making 278
Groups of transformations 391
additive (or location) 392,399
Games 310 Haar densities for 429
admissible and Bayes strategies for affine 392, 401, 407
316 Haar densities for 409
equalizer strategy for 322,325,337, matrix groups 429
379 Haar densities for 429
finite 325 multiplicative (or scale) 392
simple solution for 326 Haar densities for 429
finite strategy space for II 331,354 orthogonal 426,428
lower boundary point 335 permutation 392
minimax theorem 345
risk set 331
loss function for 311,316 Haar densities 406,409,425,429,430
maximin and minimax strategies Hide and seek 380
for 317 Hierarchical Bayes analysis 180
maximin and minimax values of comparison with empirical Bayes
317 193
players of 310 for exchangeable normal means 183
randomized strategies for 315 for general normal means 190
solving 319 Hierarchical priors, see Prior
direct method 319 distribution
finite games 325 Highest posterior density (HPD)
guess method 321,322 credible set 140, 144
S-games 331 Hunt-Stein theorem 420, 422
statistical games 349 Hyperparameters 99, 102, 180
statistical 347 Hyperplane 338
strategies for 310 Hypothesis testing
strictly determined 318 error probabilities 23, 25, 30, 44,
two-person zero-sum 311 148,356
value of 317 in Bayesian decision theory 163
Gamma distribution 560 for "O-K/' loss 164
as scale density 85 of simple hypotheses 355
conjugate prior for 287 in Bayesian inference 145, 268
invariant estimation 400 invariant 395, 404
noninformative prior for and UMP invariant 404, 428
inadmissibility 255 minimax 351, 356
f-Bayes risk 213 most powerful tests 357,524
f-minimax approach 215,222 multiple 157, 165
f-minimax regret approach 218 one-sided 147
f-posterior expected loss 205 point null hypothesis 20, 148, 268
Generalized Bayes rules 160 Bayesian and classical 20, 147,
admissibility and inadmissibility of 148, 155, 164, 508 .
254, 549, 550, 552, 553, 557 complete class 539
Subject Index 613
Jeffreys' or Lindley's paradox 156 Invariance principle 390

power function 526 Invariant decision rules 395, see also
sequential 462,477,481, 500 Invariance
significance 20, 21, 28, 202, 203 admissibility and inadmissibility of
simple hypotheses 25, 355, 481, 524 422
size 13,526 best 397, 409
inadequacies of 20, 21, 23, 30, confidence rules 414
44,202 constancy of risk functions 396
SPRT 481 Pitman's estimator 400,405
for one-sided hypotheses 500 Invariant function 402
for simple hypotheses 481 Invariant prior distribution 84, 85, 87
test function 355 Isomorphism 409
two-sided testing 538
uniformly most powerful tests 526
for one-sided hypotheses 527 Jensen's inequality 40, 343
Large sample approximations 223

Improper prior, see Prior distribution comparing Bayes to classical 125
Inadmissibility 10 in hypothesis testing 156
and long run evaluations 257 in sequential analysis 477
of Bayes rules in S-games 382 to posterior distribution 142, 170,
of formal Bayes rules 254 224
of generalized Bayes rules 254, 549, Least favorable prior distribution 350
552 Left invariant Haar density 406, 409,
of invariant rules 422 429,430
of minimax rules 360, 371 Liar's poker 381
relationship to coherency 259 Likelihood function 27
verification of 550 in sequential setting 503
of normal means 552 Likelihood principle 27, 34, 505
of Poisson means 553 and censoring 30
Incoherency 259 and noninformative priors 89
Independent opinion pool 273 derivation of 31
Inference 7, 20, see also Bayesian implies stopping rule principle 503
inference implies sufficiency 37
loss functions for 64, 166, 261 limitations of 29, 32
predictive 157 satisfied by Bayesian analysis 126,
Initial and final precision 26, 30, see 160
also Conditional perspective violated by risk functions 30
Interim analysis 504, 519 Likelihood ratio 146, 153, 484
Invariance 19, 388, see also Invariant Limited translation estimators 219
decision rules Linear opinion pool 273
and minimaxity 418 Location parameters 83, 497
and noninformative priors 390, 398, Location-scale parameters 88, 401
406, 409, 414, 424 Loss functions 3
in decision problems 393 absolute error 63
in estimation 400, 405 for inference problems 64, 166, 261
in hypothesis testing 395, 404 for randomized rules 13
location parameter problems 397, from utility functions 57
402, 404, 423 in sequential analysis 433,434, 511
location-scale problems 401, 403 invariant 393
scale parameter problems 400, 402, linear 62
424,428 matrix 7, 325
too much 421,424,431 m-inner truncated 460
614 Subject Index
Loss functions-continued Minimax decision rules 18, see also

quadratic 62 Minimax analysis
regret 60, 377 admissibility and inadmissibility of
robustness of 61, 250 371
squared-error 60 classes of 359, 363, 369
vector valued 68 sequential 501
"0-1" and "O-K/' 63 Minimax'principle 18
Lower boundary point 335 Minimax regret 377,387
Lower quantant 333 Minimax strategy 317
Minimax theorem 345
ML-II estimation, see Type II
maximum likelihood
m-inner truncated Bayes risk 460, Models
461, 468, 469 and exchangeability 106
m-inner truncated loss 460 and objectivity 110
m-step inner look ahead procedure compromising between 176
461 robustness of 248
m-step look ahead procedure 455, separation from prior 283
456,459,461 Monotone decision problems 530
m-truncated Bayes risk 448, 449, 451, estimation 534
461,467 multiple decision 530
m-truncated procedures 449 Monotone decision rules 532, 535
Marginal density 95, 128, 130, 199 Monotone likelihood ratio 357, 500,
as likelihood function 99, 177, 526
200 and uniformly most powerful tests
relative likelihoods 201 524
exchangeability of 104 Monotonization of a decision rule
in empirical Bayes theory 96, 169, 533, 535, 536
173 Multinomial distribution 562
in robustness studies 199 conjugate prior for 287
in sequential analysis 445, 450 Multiple decision problems, see Finite
information about 95 action problems
moments of 101 Multivariate normal mean 560
type II maximum likelihood 99, as location vector 83
174,223 Bayesian analysis with normal prior
Minimax analysis 308 139
comparison with Bayesian analysis HPD credible set 143
373, 379 conjugate prior for 288
conservatism 308, 376 empirical Bayes estimation 169,
finite parameter space 354 173,386
classification problems 357 gamma minimax estimation 222
testing simple hypotheses 355 generalized Bayes estimators 543
game theory 310 admissibility and inadmissibility
least favorable prior distribution 552
350, 352 hierarchical Bayes estimation 183,
regret 376, 387 190,386
sequential 501 inadmissibility of sample mean in
statistical games 347 3+ dimensions 256, 360, 552
techniques of solution 349 minimax estimators
direct method 349 class of 363
guessing a least favorable prior conflict with Bayes 367
350 sample mean 383
guessing an equalizer rule 353 with Bayesian input 220, 365,
using invariance 418 366, 368, 386
Subject Index 615
restricted risk Bayes estimation 220 minimax one-sided testing 349

robust Bayesian analysis of 236 minimax sequential estimator 501
credible regions 239, 242 ML-II prior for 235
estimation 238, 242 optimal sample size in estimation
for independent coordinates 243 435
robust priors 236, 242 optimal sample size in testing 437
with partial prior information 240 robust Bayesian analysis 239
with t-priors 245 sequential estimation with normal
priors 447
sequential testing with batches 512
Negative binomial distribution 562 SPRT for simple hypotheses 487,
conjugate prior for 287 494
likelihood function for 28 testing a point null hypothesis 20,
Neyman-Pearson lemma 524 148, 268
No-data problems 7, 13, 17, 19 UMP invariant test 428
Noninformative prior, see Prior UMP one-sided testing 529
distribution
Normal distribution 559, see also
Normal mean
as location density 83 Objectivity 90, 109, 125, 153,281
as location-scale density 88 Orbits 396
as maximum entropy distribution
93
as scale density 85 Pitman's estimator 399, 405
invariance in estimation 410,413 Poisson mean 562
noninformative prior for 84 complete class for 553
Normal form of Bayesian analysis conjugate prior for 130
160 empirical Bayes estimator 178, 297
Normal mean 559 inadmissible estimator 360
admissibility and generalized Bayes minimax estimator 360, 369, 383
estimation 543, 550, 552 noninformative prior for 114
admissibility of sample mean 548 Posterior Bayes action 159
Bayesian analysis with Posterior Bayes risk 446, 447
noninformative priors 137,289 Posterior distribution 126, 445
Bayesian analysis with normal Posterior expected loss 157
priors 127 Posterior mean 134, 136, 161
estimation 136 Posterior odds ratio 146
finite action problems 166 Posterior variance and covariance
HPD credible set 140, 208 136, 139
one-sided testing 147, 164, 210 Post-experimental and pre-
posterior robustness 208, 210, experimental, see Conditional
211, 212 perspective
testing a point null 150,211,212, Power function 526
293 Predictive analysis 66, 157
Bayesian analysis with t-priors 246, Predictive distribution 95, 157
268 Preposterior analysis 432, see also
continuous risk functions in Sequential analysis
estimation 545 optimal fixed sample size 433, 434
estimating a positive 135 Principle of rational invariance 490
gamma minimax estimation 216 Prior distribution 4, 5
invariant estimation 394, 399 classes of 97
invariant one-sided testing 394, 396 e-contamination 98, 100, 197,
limited translation estimates 219 206, 222, 232, 233
minimax estimation 350 in hypothesis testing 154
616 Subject Index
Prior distribution, classes of-continued of Bayesian analysis 120, 198

of given functional form 97, 197 of game theory and minimax
of given structural form 97 analysis 308,318, 371
conjugate 130 type II 34
construction from marginal 94 R-better 10
distance approach 103 R-equivalent 10
ML-II approach 101 Restricted risk Bayes principle 22
moment approach 101 Rewards 47
construction of subjectively 77 Right invariant Haar densities 406,
CDF determination 81 409, 425, 429, 430
elicitation difficulties 76, 82, 112 Risk functions 9, 13, 23, 34
given a functional form 78, 245 continuous 254, 544
histogram approach 77 of sequential procedures 442
multivariate 81, 112 use in Bayesian robustness 218
relative likelihood approach 77 Risk point 331
using the robust form 237,240 Risk set 331
hierarchical 106, 180,237,245 Robustness 69
improper 82, 87, 132, 160 and ignoring data 251
as an approximation 90, 229 of Bayes rules 195, 285
inadmissibility of 254 r-minimax analysis 215, 222
invariant (right and left) and r-minimax regret 218
relatively invariant 84, 85, 87, in estimation 208, 226
290, 409, 413, 416 in testing 211, 226
least favorable 350 posterior measures 205
maximum entropy 90 risk measures 213, 218
ML-II 99 use of minimaxity 378
noninformative 33, 82, 87, 132, 135, with e-contamination class 206
160 of conjugate priors 195, 228
and classical statistics 137,406 of empirical Bayes estimators 167
and entropy 92 of hierarchical priors 231
and invariance 83, 398,406,409, of losses 61, 250
412,413 of maximum entropy priors 94
and minimaxity 309, 350, 378 of ML-II priors 232
as an approximation 90, 229 of models 248
for binomial parameters 89 of noninformative priors 229
for location parameters 84 of priors 34, 111, 195, 236
for location-scale parameters 88, for determining sample size 441
409 stable estimation 223
for Poisson parameters 114 use of the marginal for 199,248
for scale parameters 85
in hierarchical situations 187, 192
Jeffreys' prior 87 Scale parameters 85,400
robustness of 229 Scissors-paper-stone 380
reference informative 153 Scoring rules 66
robustness of, see Robustness Sensitivity analysis 196, 247
robust priors 228, 236, 245 Separating hyperplane 339
P-values 147, 151, 155 Separating hyperplane theorem 339
Sequential analysis 433, 441
Bayesian 442
Randomized decision rules 12, 18,36, decision rules 446
40, 315, 348, 397 existence of Bayes procedure
Rao-BlackwelI theorem 41 469, 472, 473
Rationality 120, 198 procedures for constant posterior
and invariance 390 risk 447
Subject Index 617
finding and approximating Bayes Sufficient statistics 35

procedures 448 and convex loss 41
accuracy of approximations 462 and posterior distributions 127
asymptotically pointwise optimal complete class 36, 422
477 in sequential analysis 506
inner truncation 459 Supporting hyperplane 339
look ahead procedures 455 Supporting hyperplane theorem 339
solving the functional equation
474,482
truncated procedures 448 Table entry problem 86
loss function for 433, 434, 511 t -distribution 561
minimax procedures 501 as location density 83
stopping rule principle 502 as scale density 88
testing simple hypotheses 481 Test functions 355
Sequential batch sampling 512 Transitive group 397, 405
Sequential decision procedures 441 Truncated procedures, see m-truncated
Bayes 445 procedures
existence of 469 Type I and type II errors, see
minimax 501 Hypothesis testing; error
proper 442 probabilities
Sequential probability ratio test Type II maximum likelihood 99
(SPRT) 481, 485, 486
admissibility of 498
as a Bayes procedure 482, 499 Unbiased estimator of risk 361
generalized SPRT 540 for normal means 362, 386
one-sided testing 500 for Poisson means 363, 386
Wald approximations 485 Uniform distribution 560
accuracy of 495 credible sets for 290
Sequential sample 433 invariant estimation 428
S-games 331, 338 sequential Bayes 474, 516, 520
Significance testing; see Hypothesis Uniformly most powerful 326
testing Utility 47
Stable estimation (or stable Utility functions 47
measurement) 223 and loss functions 57
Stein phenomenon 360 construction of 48, 53
Stein's necessary and sufficient axioms for 49
condition for admissibility 546 for money 53
Stopping rules 441 in game theory and minimax
evidential relevance of 502 analysis 313,314,376
informative 510 in sequential analysis 433
Stopping rule principle 502 multidimensional 53
and admissibility 509
criticisms of 506
Stopping time 442
Value (of a game) 318
St. Petersburg paradox 57, 71
Strategies 310
Strictly determined game 318
Student's t-distribution, see Wald approximations (for an SPRT)
t -distribution 492
Subjective probability 74, 198 accuracy of 495
Sufficient partition 36 Weak conditionality principle 31
Springer Series in Statistics (continued from p. ii)
Huet/Bouvier/Poursat/Jolivet: Statistical Tools for Nonlinear Regression: A Practical

Guide with S-PLUS and R Examples, 2nd edition.
Ibrahim/Chen/Sinha: Bayesian Survival Analysis.
Jolliffe: Principal Component Analysis, 2nd edition.
Knattnerus: Sample Survey Theory: Some Pythagorean Perspectives.
Kolen/Brennan: Test Equating: Methods and Practices.
Kotz/Johnson (Eds.): Breakthroughs in Statistics Volume I.
Kotz/Johnson (Eds.): Breakthroughs in Statistics Volume II.
Kotz/Johnson (Eds.): Breakthroughs in Statistics Volume m.
Kuchler/S;rensen: Exponential Families of Stochastic Processes.
Kutoyants: Statistical Influence for Ergodic Diffusion Processes.
Lahiri: Resampling Methods for Dependent Data.
Le Cam: Asymptotic Methods in Statistical Decision Theory.
Le CamlYang: Asymptotics in Statistics: Some Basic Concepts, 2nd edition.
Liu: Monte Carlo Strategies in Scientific Computing.
Longford: Models for Uncertainty in Educational Testing.
Manski: Partial Identification of Probability Distributions.
Mielke/Berry: Permutation Methods: A Distance Function Approach.
Pan/Fang: Growth Curve Models and Statistical Diagnostics.
Parzen/Tanabe/Kitagawa: Selected Papers of Hirotugu Akaike.
Politis/Romano!Wolf: Subsampling.
Ramsay/Silverman: Applied Functional Data Analysis: Methods and Case Studies.
Ramsay/Silverman: Functional Data Analysis.
Rao/Toutenburg: Linear Models: Least Squares and Alternatives.
Reinsel: Elements of Multivariate Time Series Analysis, 2nd edition.
Rosenbaum: Observational Studies, 2nd edition.
Rosenblatt: Gaussian and Non-Gaussian Linear Time Series and Random Fields.
Siirndol/Swensson!Wretman: Model Assisted Survey Sampling.
Santner!Williams/Notz: The Design and Analysis of Computer Experiments.
Schervish: Theory of Statistics.
Shao/Tu: The Jackknife and Bootstrap.
Simonaff: Smoothing Methods in Statistics.
Singpurwalla and Wilson: Statistical Methods in Software Engineering:
Reliability and Risk.
Small: The Statistical Theory of Shape.
Sprott: Statistical Inference in Science.
Stein: Interpolation of Spatial Data: Some Theory for Kriging.
Taniguchi/Kakizawa: Asymptotic Theory of Statistical Inference for Time Series.
Tanner: Tools for Statistical Inference: Methods for the Exploration of Posterior
Distributions and Likelihood Functions, 3rd edition.
van der Laan: Unified Methods for CensorelLongitudinal Data and Causality.
van der Vaart/Wellner: Weak Convergence and Empirical Processes: With
Applications to Statistics.
Verbeke/Molenberghs: Linear Mixed Models for Longitudinal Data.
Weerahandi: Exact Statistical Methods for Data Analysis.
West/Harrison: Bayesian Forecasting and Dynamic Models, 2nd edition.

Common Statistical Densities: Appendix 1

Uploaded by

Document Informationclick to expand document information

Copyright:

Available Formats

Common Statistical Densities: Appendix 1

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Common Statistical Densities: Appendix 1

Uploaded by

Copyright:

Available Formats

APPENDIX 1

Common Statistical Densities

f(a) = LX> e-Xx",-t dx.

We first list the continuous densities, followed by the discrete densities.

f(xllL (72) = 1 e-(x- JL )2/ 2 u 2

Mean = IL, Variance = (72.

2. p-Variate Normal (.N'p(fI., I»: ~= RP, fI. = (ILI>"" ILp)t E RP, I is a

Mean = fl., Covariance matrix = I.

Mean =!(a + (3), Variance = (f3 - a)2/12.

4. Gamma (C§(a,f3»: f£= (0, (0), a>O, f3>0, and

f(xla, (3) = f(a\f3 a x a - I e- x //3 I(o,oo)(x).

Mean = af3, Variance = af32.

5. Beta (i?)J£(a,f3»: f£=[0, 1], a>O, f3>0, and

Mean = a/(a + (3), Variance = af31(a + (3)2(a + f3 + 1).

6. Cauchy (C€(a,f3»: f£=R\ -oo<a<oo, f3>0, and

f(xla, (3) = '7T[f32+~X - a?f

8. t distribution with a degrees of freedom, location parameter /L, and

2 f[( a + I)/2] ( (x - /L)2 ) -(a+I)/2

Mean = /L, if a> 1, Variance = a(72/(a - 2) if a> 2.

9. p- Variate t distribution with a degrees of freedom, location vector fl.,

Mean = fl. if a> 1, Covariance matrix = aI/(a -2) if a> 2.

10. Inverse Gamma (~C§(a,f3)): 2l'=(0, 00), a>O, f3>0, and

f(xla, f3) = f(a)f3:x(a+1) e- l / x /3 I(o,oo)(x).

Mean = II f3(a -1) if a> 1, Variance = II f32(a -I)2(a -2) if a> 2.

11. Dirichlet (f!O(a)):x=(X),,,.,Xk)' where L~=lxj=1 and O:sxj:sl

Mean (X;}=aJao, Variance (Xj)=(ao-a;}aJa~(ao+l), Covariance

f(xlxo, a)=: (:or+1I(Xo,OO)(X).

Mean = aXo/(a -1) if a> 1.

f(xln, p) = (;) pX(1- p)(n-xl,

Mean = a(1- p)/p, Variance = a(1- p)/p2.

I. Definition and Properties of Hm

A good approximation to Hm , for most purposes, is

Some expressions for Hm in terms of standard special functions are

Hm(v) = [evr(; + 1) v- m/ 2Pm(2v) r 1

where Pm is the c.d.f. of the chi-square distribution with m degrees of

Hm(v) = [1 + i~dm/2+ 1)(m/2:~) ... (m/2+ i)r 1

and a recurrence relation is

II. Development of (4.121) and (4.122)

Hf.11Tk(Bx) and HV 1T k(Bx)W.

Finally, the posterior mean and covariance matrix of 0, with respect to

f.11T*(X) = E 1T *(O\x)[O] = E 1T *(O\x)[PO]+ E 1T *(O\x)[(1 - P)O]

and (using the posterior independence of PO and (I - P)O)

V 1T *(x) = E 1T *(O\x)[(O - f.11T* (x»(O - f.11T* (x) n

III. Verification of Formula (4.123)

results in the following approximation to 7T;(0, u 2 lx, S2):

?Tp(Olx, S2) = k(x, S2) too f(0)u- 2h(S2Iu2)du2.

?Tn(Olx, S2) = k*(x, S2) too u- p exp { - 2: 22.(0, x, S2)} u- m

which is the expression in (4.123).

. replacing u 2 by 0- 2 is a reasonable approximation, in that any resultant

I. Verification of Formula (7.8)

= ( - -n2) 1/2 exp { --2(K(n)-8)2

Integrating by parts shows that

= (27Tn(1"2) -1/2 exp { - 2: 2 (K (n) - O)2}

~ r( 7T, 8~) = L. L( 0, ao)(27Tn(1"2)-1/2 exp { - 2:2 (K(n) - O)2}

x[nK'(n) +HK(n) - O)]dP1T( 0)

X[nK'(n) +!(K(n) - 8)]dP1T( 0).

II. Verification of Formula (7.10)

Using this in (7.6) and eliminating common constants gives

f.11T(X) = E 1T (O\x)[O] = E 1T (O\x)[PO]+ E 1T (O\x)[(1 - P)O]

V 1T (x) = E 1T (O\x)[(O - f.11T* (x»(O - f.11T* (x) n