Sampling Distributions and

Point Estimation of
Parameters

LESSON 6
 Point Estimation
Statistical inference is always
focused on drawing conclusions
about one or more parameters of
a population.
An important part of this process
is obtaining estimates (reasonable
values) of the parameters.
 Point Estimation
Since a statistic is a random
variable, it has a probability
distribution. We call the proba-
bility distribution of a statistic a
sampling distribution.
 Point Estimation
In general if X is a random
variable with probability
distribution f(x) characterised by
the unknown parameter 𝛉, and if
X1, X2,…,Xn is a random sample
of size n from X, the statistics
Θ̂ = h( X 1 ,X 2 ,… ,X n )
 Point Estimation
is called a point estimator of 𝛉

A point estimate of some

population θ is a single
numerical value θ̂ of a
statistic Θ̂ .
We often need to estimate:
∗ the µ of a single population
∗ the σ of a single population
2

∗ µ1 − µ2
∗ p1 − p2
Reasonable point estimates of
these parameters are as follows:

∗ for µ , µ̂ = x
∗ for σ , σ̂ = s
2 2 2

∗ for p, p̂ = x n
∗ for p1 − p2 , p̂1 − p̂2
The link between the probability
models in the earlier chapters and
the data is made as follows:
• Each numerical value in the data
is the observed value of a
random variable.
• The random variables are usually
assumed to be independent and
identically distributed. These
random variables are known as a
random sample.
 Definition
The random variables
X 1 , X 2 ,… ,X n are random
sample of size n if (a) the
X i ' s are independent random
variable, and (b) every X i has
the same probability distribution
 Definitions
Statistic
A statistic is any function of the
observations in a random sample

Sampling Distribution
The probabilty distribution of a
statistic is called a sampling distribution
 Definitions
Central Limit Theorem

If X 1 ,X 2 ,… ,X n is a random sample
of size n taken from a population
(either finite or infinite) with mean
µ and finite variance σ , and if X
2
 Definitions
Central Limit Theorem

is the sample mean, the limiting form

X −µ
of the distribution of z = as
σ n
n → ∞, is the standard normal
distribution
 Example 1
An electronics company
manufactures resistors that have a
mean resistance of 100 ohms and a
standard deviation of 10 ohms. The
distribution of resistance is normal.
Find the probability that a random
sample of n ︎= 25 resistors will have an
average resistance less than 95 ohms.
Solution for Example 1
The sampling distribution of X is
normal, with mean µ x = 100 Ω
and a standard deviation of
σ 10
σX = = = 2, therefore,
n 25
95 − 100
z= = −2.5
2
 Solution for Example 1
7_223-250.qxd 1/11/10 7:52 PM Page 229

Therefore,
P( X < 95 )SAMPLING
= P(DISTRIBUTIONS
7-2 Z < −2.5 )THE CENTRAL LIMIT
AND

= 0.0062 4 5

σX = 2

95 100 x 4 5

Figure 7-2 Probability for Example 7-1. Figure 7-3 The distri
for Example 7-2.
708 APPENDIX A STATISTICAL TABLES AND CHARTS

708 APPENDIX A STATISTICAL TABLES AND CHARTS z

!
1 1
!2 u
2

"1z2 # P1Z $ z2 # e du
!% 22&
z

!
1 ! 12 u
2

"1z2 # P1Z $ z2 # e du
!% 22&

Φ (z)

Φ (z)
z 0

z 0

Cumulative Standard Normal Distribution

Table III Cumulative Standard Normal Distribution

zTable III
!0.09Cumulative
!0.08Standard Normal Distribution
!0.07 !0.06 !0.05 !0.04 !0.03 !0.02 !0.01 !0.00
!3.9 0.000033 0.000034 0.000036 0.000037 0.000039 0.000041 0.000042 0.000044 0.000046 0.000048
z !0.09 !0.08 !0.07 !0.06 !0.05 !0.04 !0.03 !0.02 !0.01 !0.00
!3.8 0.000050 0.000052 0.000054 0.000057 0.000059 0.000062 0.000064 0.000067 0.000069 0.000072
!3.7!3.90.000075
0.0000330.000078
0.0000340.000082
0.000036 0.000085
0.000037 0.000088
0.000039 0.000041
0.000092 0.000042
0.000096 0.000044
0.000100 0.000046
0.000104 0.000048
0.000108
!3.8 0.000050 0.000052 0.000054 0.000057 0.000059 0.000062 0.000064 0.000067 0.000069 0.000072
!3.6 0.000112 0.000117 0.000121 0.000126 0.000131 0.000136 0.000142 0.000147 0.000153 0.000159
!3.7 0.000075 0.000078 0.000082 0.000085 0.000088 0.000092 0.000096 0.000100 0.000104 0.000108
!3.5 0.000165 0.000172 0.000179 0.000185 0.000193 0.000200 0.000208 0.000216 0.000224 0.000233
!3.6 0.000112 0.000117 0.000121 0.000126 0.000131 0.000136 0.000142 0.000147 0.000153 0.000159
!3.4 0.000242 0.000251 0.000260 0.000270 0.000280 0.000291 0.000302 0.000313 0.000325 0.000337
!3.5 0.000165 0.000172 0.000179 0.000185 0.000193 0.000200 0.000208 0.000216 0.000224 0.000233
!3.3 0.000350 0.000362 0.000376 0.000390 0.000404 0.000419 0.000434 0.000450 0.000467 0.000483
!3.4 0.000242 0.000251 0.000260 0.000270 0.000280 0.000291 0.000302 0.000313 0.000325 0.000337
!3.2 0.000501 0.000519 0.000538 0.000557 0.000577 0.000598 0.000619 0.000641 0.000664 0.000687
!3.3 0.000350 0.000362 0.000376 0.000390 0.000404 0.000419 0.000434 0.000450 0.000467 0.000483
!3.1 0.000711 0.000736 0.000762 0.000789 0.000816 0.000845 0.000874 0.000904 0.000935 0.000968
!3.2 0.000501 0.000519 0.000538 0.000557 0.000577 0.000598 0.000619 0.000641 0.000664 0.000687
!3.0 0.001001 0.001035 0.001070 0.001107 0.001144 0.001183 0.001223 0.001264 0.001306 0.001350
!3.1 0.000711 0.000736 0.000762 0.000789 0.000816 0.000845 0.000874 0.000904 0.000935 0.000968
!2.9 0.001395 0.001441 0.001489 0.001538 0.001589 0.001641 0.001695 0.001750 0.001807 0.001866
!3.0 0.001001 0.001035 0.001070 0.001107 0.001144 0.001183 0.001223 0.001264 0.001306 0.001350
!2.8!2.90.001926
0.0013950.001988
0.0014410.002052
0.001489 0.002118
0.001538 0.002186
0.001589 0.002256
0.001641 0.002327
0.001695 0.002401
0.001750 0.002477
0.001807 0.002555
0.001866
!2.7!2.80.002635
0.0019260.002718
0.0019880.002803
0.002052 0.002890
0.002118 0.002980
0.002186 0.003072
0.002256 0.003167
0.002327 0.003264
0.002401 0.003364
0.002477 0.003467
0.002555
!2.6!2.70.003573
0.0026350.003681
0.0027180.003793
0.002803 0.003907
0.002890 0.004025
0.002980 0.004145
0.003072 0.004269
0.003167 0.004396
0.003264 0.004527
0.003364 0.004661
0.003467
!2.5!2.60.004799 0.004940 0.005085 0.005234
0.003573 0.003681 0.003793 0.003907 0.0040250.005386 0.005543
0.004145 0.005703
0.004269 0.005868
0.004396 0.006037
0.004527 0.006210
0.004661
!2.4!2.50.006387
0.0047990.006569
0.0049400.006756
0.005085 0.006947
0.005234 0.007143
0.005386 0.007344
0.005543 0.007549
0.005703 0.007760
0.005868 0.007976
0.006037 0.008198
0.006210
!2.3!2.40.008424
0.0063870.008656
0.0065690.008894
0.006756 0.009137
0.006947 0.009387
0.007143 0.009642
0.007344 0.009903
0.007549 0.010170
0.007760 0.010444
0.007976 0.010724
0.008198
!2.2!2.30.011011
0.0084240.011304
0.0086560.011604
0.008894 0.011911
0.009137 0.012224
0.009387 0.012545
0.009642 0.012874
0.009903 0.013209
0.010170 0.013553
0.010444 0.013903
0.010724
!2.1!2.20.014262
0.0110110.014629
0.0113040.015003
0.011604 0.015386
0.011911 0.015778
0.012224 0.016177
0.012545 0.016586
0.012874 0.017003
0.013209 0.017429
0.013553 0.017864
0.013903
!2.0 0.018309 0.018763 0.019226 0.019699 0.020182 0.020675 0.021178 0.021692 0.022216 0.022750
General Concepts of Point Estimation

Bias of an Estimator
The point estimator Θ̂ is an unbiased
estimator fr the parameter θ if E( Θ̂ ) = θ
If the estimator is not unbiased, then the
difference E( Θ̂ ) − θ is called the bias of
the estimator Θ̂ .
 Example
x1 x2 x3 x4 x5

12.8 9.4 8.7 11.6 13.1

x6 x7 x8 x9 x10

9.8 14.1 8.5 12.1 10.3

 Solution
Sample Mean
10

∑x i
x= i=1
= 11.04
10
Sample Median
10.3 + 11.6
!x = = 10.95
2
 Solution
10% Trimmed Mean; discarding
8.5 and 14.1 before averaging
xtr ( 10 ) = 10.98
These are unbiased estimates of
µ ; no unique unbiased estimator.
But, we cannot rely on the
property of unbiasedness alone:
Standard Error of an Estimator
The standard error of an estimator
Θ̂ is its standard deviation, given by
( )
σ Θ̂ = V Θ̂ . If the standard error
involves unknown parameters that
can be estimated, substitution of
those values into σ Θ̂ produces an
estimated standard error σ̂ Θ̂ .
 Example
An article in the Journal of Heat
Transfer (Trans. ASME, Sec. C, 96,
1974, p. 59) described a new method
of measuring the thermal conductivity
of Armco iron. Using a temperature of
100︎F and a power input of 550 watts,
the following 10 measurements of
thermal conductivity (in Btu/hr-ft-︎F)
were obtained:
 Example
x1 x2 x3 x4 x5

41.60 41.48 42.34 41.95 41.86

x6 x7 x8 x9 x10

42.18 41.72 42.26 41.81 42.04

 Example
A point estimate of the mean thermal
conductivity at 100 oF and 550 watts
is the sample mean or

x = 41.924 BTU / hr − ft − °F
The standard error of the sample
mean is σ X = σ n since 𝞂 is ︎

unknown, sample standard

deviation, s = 0.284 may replace 𝞂
σ̂ X = s n
= 0.284 10
= 0.0898
this is 0.2% of the sample mean.
If we can assume that thermal
conductivity is 2 ( 0.089 ) = 0.1796,
then,41.924 is between
41.924 ± 0.1796
Lesson 2 Part 2

Statistical Intervals for

a Single Sample
Earlier, an illustration of how a
point estimate of parameter can
be estimated. However, it is
important to understand how
good is the estimate obtained,
because of sampling variability,
it is almost never the case that
the true mean ︎ is exactly equal
to the estimate x.
Information about the precision
of estimation is conveyed by the
length of the interval. A short
interval implies precise
estimation.

Three types of intervals are as

follows:
 INTERVALS

Confidence Tolerance Confidence

Interval Interval Interval
A c o n fi d e n c e i n t e r v a l b o u n d s
population or distribution parameters
(such as the mean viscosity).
A tolerance interval is another
important type of interval estimate. A
tolerance interval bounds a selected
proportion of a distribution.
Confidence and tolerance intervals
bound unknown elements of a
distribution.
A prediction interval provides bounds
on one (or more) future observations
from the population. With a large
sample size, the prediction interval
for normally distributed data tends to
the tolerance interval, but for more
modest sample sizes the prediction
and tolerance intervals are different.
 Single Sample:
Estimating the Mean
The sampling distribution of “X-bar”
is centered at µ, and in most
applications the variance is smaller
than that of any other estimators of
µ. Therefore, the sample mean “x-
bar” will be used as a point estimate
for the population mean µ.
 Single Sample:
Estimating the Mean
According to the Central Limit Theorem,
we can expect the sampling distribution
of “X-bar” to be approximately normally
distributed with mean µ x = µ
and standard deviation σ x = σ n
 Single
Chapter 9 One-Sample:
Estimation
and Two-Sample
Chapter 9 One- and Two-Sample Est
Estimating
√ the Mean
ion σX̄ = σ/ n. Writing zα/2 for the z-value above wh
Writing
under the z√
normal for the
α/2 curve, wez-value
can see above
from which
Figure 9.2 tha
on σ = σ/ n. Writing z α/2 for the z-value ab
we find an area of α/2 under the normal
X̄
under the
P normal
(−z < curve,
Z < z we
) = can
1 − see
α, from Figure
curve, weα/2can seeα/2
from the figure that

P (−zα/2 < Z < zα/2 ) = 1 − α,

where X̄ − µ
Z= √ .
σ/ n
X̄ − µ
Z= √ .
! σ/ n"
X̄ − µ
 Single Sample:
Chapter 9 One- and Two-Sample Estimation Problems

√
X̄ − µ
standard deviation σX̄ = σ/ n. Writing zα/2 for the z-value above which we find

√ .
an area of α/2 under the normal curve, we can see from Figure 9.2 that
Z=
Estimatingσ/the
n Mean
P (−zα/2 < Z < zα/2 ) = 1 − α,

where

Hence, Z=
X̄ − µ
√ .
σ/ n
!
Hence,
"
! X̄ − µ "
P −zα/2 < X̄ −√ = 1 − α.
√ < z <=z
µ
P −z < 1 α/2
− α.
σ/
σ/ n n
α/2 α/2

1−α

α /2 α /2 z
−zα /2 0 zα /2

1−α
Figure 9.2: P (−zα/2 < Z < zα/2 ) = 1 − α.
 Confidence Interval on µ,
2
σ Known
If “x-bar” is the mean of a random
sample of size n from a population with
2
known variance σ , a 100(1 − α)%
confidence interval for μ is given by

σ σ
x − zα 2 < µ < x + zα 2
n n
where zα/2 is the z-value leaving an area
of α/2 to the right.
Illustration
The average zinc concentration
recovered from a sample of
measurements taken in 36 different
locations in a river is found to be 2.6
grams per millilitre. Find the 95% and
99% confidence intervals for the
mean zinc concentration in the river.
Assume that the population standard
deviation is 0.3 gram per milliliter.
 √
standard deviation σX̄ = σ/ n. Writing zα/2 for the z-value above which we fin
an area of α/2 under the normal curve, we can see from Figure 9.2 that

Solution
P (−zα/2 < Z < zα/2 ) = 1 − α,

where
X̄ − µ
Z= √ .

The point estimate of μ is

σ/ n

Hence,
!
x = 2.6 "
X̄ − µ
P −zα/2 < √ < zα/2 = 1 − α.
σ/ n

The z-value leaving an

area of 0.025 to the
right, and therefore an
1−α

area of 0.975 to the α /2

−zα /2 0
α /2
zα /2
z

left, is z0.025 = 1.96 Figure 9.2: P (−zα/2 < Z < zα/2 ) = 1 − α.

√
Multiplying each term in the inequality by σ/ n and then subtracting X̄ from eac
(See Z Table). term and multiplying by −1 (reversing the sense of the inequalities), we obtain
! "
σ σ
P X̄ − zα/2 √ < µ < X̄ + zα/2 √ = 1 − α.
n n

A random sample of size n is selected from a population whose variance σ 2 is known

and the mean x̄ is computed to give the 100(1 − α)% confidence interval below. I
is important to emphasize that we have invoked the Central Limit Theorem above
 e that the population standard deviation is 0.3 gram per milli
oint estimate of µ is x̄ = 2.6. The z-value leaving an area of

Solution
and therefore an area of 0.975 to the left, is z0.025 = 1.96 (Table
% confidence interval is
! " ! "
0.3 0.3
2.6 − (1.96) √ < µ < 2.6 + (1.96) √ ,
36 36

which reduces to 2.50 < μ < 2.70

To find a 99% confidence interval, we find the z-
value leaving an area of 0.005 to the right and
0.995 to the left. From the Z-Table again,
z0.005 = 2.575, and the 99% confidence interval is
 s to 2.50
educes < µ< <
to 2.50 µ< 2.70.
2.70. To
To find
find aa99%
99%confidence
confidence in
interva
ng Solution
an area
leaving of 0.005
an area of 0.005totothe
the right and0.995
right and 0.995 to the
to the left. lef
Fr
z= = 2.575,
2.575,
0.005 andandthethe99%
99%confidence
confidence interval is is
interval
! " ! "
! 0.3" !
0.3 "
2.6 − (2.575) 0.3√ < µ < 2.6 + (2.575) √ 0.3,
2.6 − (2.575) √ 36 < µ < 2.6 + (2.575) 36√
36 36
ly
or simply
2.47 < µ < 2.73.
2.47 is
w see that a longer interval <required
µ < 2.73.
to estimate µ with a hi
nce.
hat a longer
100(1−α)% intervalinterval
confidence is required toan
provides estimate
estimate µ
of with
the a
stimate. If µ is actually the center value of the interval, the
out error. confidence
1−α)% Most of the interval
time, however, x̄ willannot
provides be exactly
estimate of et
nt estimate will be in error. The size of this error will be the
Theorem

If x is used as an estimate of μ,
we can be 100(1 − α)%
confident that the error
σ
will not exceed zα 2
n
Theorem
If x is used as an estimate of μ, we can be
100(1 − α)% confident that the error will
not exceed a specified amount e when the
sample size is
⎛ zα 2σ ⎞
2

n=
⎜⎝ e ⎟⎠
Illustration
How large a sample is required
if we want to be 95% confident
that our estimate of μ in
illustration above is off by less
than 0.05?
Solution
The population standard deviation is σ =
0.3. According to this theorem:

If x is used as an estimate of μ, we can

be 100(1 − α)% confident that the error
will not exceed a specified amount e
when the sample size is ⎛ zα 2σ ⎞
2

n=
⎜⎝ ⎟
e ⎠
9.2 is off by less than 0.05?
tandard deviation is σ = 0.3. Then, by Theo
! "2
(1.96)(0.3)
n= = 138.3.
0.05
be 95% confident that a random sample of s
Therefore, we can be 95% confident
ering from µ by an amount less than 0.05.
that a random sample of size 139 will
provide an estimate x differing from

dsμ by an amount less than 0.05.

ntervals and resulting confidence bounds dis
th upper and lower bounds are given). Howe
Confidence Interval on µ,
2
σ not known
In the preceding slides we used
the terms “confident” and
“interval.”
When estimating a population
parameter using a sample
statistic it is never going to be
perfect; tere will always be error
built-in, so we take sample.
We can express the error, or
uncertainty, using an interval
estimate following the form

Point Estimate ± Margin of Error

Confidence Intervals
Population Deviation Unknown
To find the standard deviation of
the mean (SEM) we need to know
two things: (a) the population
standard deviation and (b) the
same size. (Most often we do not
know the population SD and
therefore we have to estimate it.
Confidence Intervals
Population Deviation Unknown

Also remember that for any

population SD or its estimate,
increasing the sample size (up
to a point) reduces standard
error
Confidence Intervals
270 Chapter 9 One- and Two-Sample Estimation Problems

√
standard deviation σX̄ = σ/ n. Writing zα/2 for the z-value above which we find
an area of α/2 under the normal curve, we can see from Figure 9.2 that

Population Deviation Unknown where

P (−zα/2 < Z < zα/2 ) = 1 − α,

X̄ − µ
Z= √ .
σ/ n

Just remember Hence,

!
X̄ − µ
"

that we are dealing

P −zα/2 < √ < zα/2 = 1 − α.
σ/ n

with a normal
curve where the 1−α

area under the α /2

0
α /2 z

curve is equal to 1
−zα /2 zα /2

Figure 9.2: P (−zα/2 < Z < zα/2 ) = 1 − α.

and the probability

√
Multiplying each term in the inequality by σ/ n and then subtracting X̄ from each
term and multiplying by −1 (reversing the sense of the inequalities), we obtain
! "

under the curve is

σ σ
P X̄ − zα/2 √ < µ < X̄ + zα/2 √ = 1 − α.
n n

also equal to 1
A random sample of size n is selected from a population whose variance σ 2 is known,
and the mean x̄ is computed to give the 100(1 − α)% confidence interval below. It
is important to emphasize that we have invoked the Central Limit Theorem above.
As a result, it is important to note the conditions for applications that follow.

Confidence If x̄ is the mean of a random sample of size n from a population with known
Interval on µ, σ 2 variance σ 2 , a 100(1 − α)% confidence interval for µ is given by
 √
standard deviation σX̄ = σ/ n. Writing zα/2 for the z-value above which we fin

Confidence Intervals
an area of α/2 under the normal curve, we can see from Figure 9.2 that

P (−zα/2 < Z < zα/2 ) = 1 − α,

Population Deviation Unknown

where
X̄ − µ
Z= √ .
σ/ n

Hence,

When we do not !
P −z <
X̄ − µ
√ <z
"
α/2 = 1 − α. α/2
σ/ n
know population SD,
we have to estimate
it. This estimate 1−α
(uncertainty) forces
us to use the α /2
0
/2 z α

s t u d e n t ’s t-
−z α /2 z α /2

Figure 9.2: P (−z < Z < z ) = 1 − α.

α/2 α/2

distribution instead √
Multiplying each term in the inequality by σ/ n and then subtracting X̄ from eac

of normal distribution
term and multiplying by −1 (reversing the sense of the inequalities), we obtain
!
σ σ
"
P X̄ − zα/2 √ < µ < X̄ + zα/2 √ = 1 − α.
n n

A random sample of size n is selected from a population whose variance σ 2 is known

and the mean x̄ is computed to give the 100(1 − α)% confidence interval below. I
is important to emphasize that we have invoked the Central Limit Theorem above
Characteristics of t-
distribution
In general, the t-distribution is
shorter in the middle and fatter
in the tails
Characteristics of t-
distribution
More probability in the tails, less
near the mean, greater chance
of extreme values
Characteristics of t-
distribution
There isn’t just one t-distribution
There is a t-distrbution for every
sample size
Characteristics of t-
distribution
Degrees of Freedom (n-1)
Smaller the sample size, the
shorter and fatter the distribution;
more tail probability
However, as n becomes large, the
t-distribution converges towards z-
distribution
 α /2 α /2
Confidence
−t α 2 Interval
0 on μ, tα 2
σ Unknown
2
Figure 9.5: P (−tα/2 < T < tα/2 ) = 1 − α.
If “x-bar” and s are the mean and
standard deviation of a random
sample from a normal population
re the mean and standard deviation
2 of
with unknown variance σ2 , a 100(1−α)a random
lation with unknown variance σ , a 100(1 − α)% co
% confidence interval for μ is

s s
x̄ − tα/2 √ < µ < x̄ + tα/2 √ ,
n n
s the t-value with v = n − 1 degrees of freedom, le
 −t α 2 0 tα 2
Confidence Interval on μ,
Figure 9.5:σ2PUnknown
(−tα/2 < T < tα/2 ) = 1 − α.

where tα/2 is the t-value with v = n − 1

degrees of freedom, leaving an area
are the mean and standard deviation of a rando
of α/2 to the right. 2
ulation with unknown variance σ , a 100(1 − α)% c

s s
x̄ − tα/2 √ < µ < x̄ + tα/2 √ ,
n n
is the t-value with v = n − 1 degrees of freedom, l
right.
onfidence interval estimates. We should emphasize
the Central Limit Theorem, whereas for σ unkno
Confidence Interval on μ,
ng distribution of the random variable T . However
σ Unknown
2
s based on the premise that the sampling is from a no
he distribution is approximately bell shaped, confid
Computed
2 one-sided confidence
when σ is unknown by using the t-distribution an
bounds
sults. for μ with σ unknown are as
the reader would expect, namely
d one-sided confidence bounds for µ with σ unknown
, namely
s s
x̄ + tα √ and x̄ − tα √ .
n n
upper and lower 100(1 − α)% bounds, respective
g an area of α to the right.
Illustration
The contents of seven similar
containers of sulfuric acid are 9.8,
10.2, 10.4, 9.8, 10.0, 10.2, and 9.6
liters. Find a 95% confidence interval
for the mean contents of all such
containers, assuming an
approximately normal distribution.
 n n
upper and lower 100(1 − α)% bounds, respectiv
Solution
an area of α to the right.

of seven similar containers of sulfuric acid are 9

The sample mean and standard
9.6 liters. Find a 95% confidence interval for th
deviation for the given data are:
ners, assuming an approximately normal distribu
ean and standard deviation for the given data ar

x̄ = 10.0 and s = 0.283.

.4, we find t0.025 = 2.447 for v = 6 degrees of fr

Solution
Using t-distribution Table, we find
t0.025 = 2.447 for v = 6 degrees of
freedom. Hence, the 95% confidence
interval for μ is
 Solution Chapter 9 One- and Two-Sample Estima

nfidence interval for µ is

! " ! "
0.283 0.283
10.0 − (2.447) √ < µ < 10.0 + (2.447) √ ,
7 7
educes to 9.74 < µ < 10.26.
which reduces to
Sample Confidence
9.74 < Interval
μ < 10.26.
tatisticians recommend that even when normality cannot be
wn, and n ≥ 30, s can replace σ and the confidence interval
s
x̄ ± zα/2 √
 ! " !
0.283 0.
.0 −Concept
(2.447) of
√ a Large-Sample
< µ < 10.0 + (2.447) √
7
Confidence Interval
s toOften
9.74 < statisticians
µ < 10.26. recommend that
even when normality cannot be
ple assumed,
Confidence σ is unknown,
Interval and n ≥ 30, s
can replace σ and the confidence
cians recommend that even when normality
interval, often referred to as a large- ca
≥ 30, s confidence
d n sample can replace σinterval,
and theuse
confidence in
s
x̄ ± zα/2 √
n
Illustration
S c h o l a s t i c A p t i t u d e Te s t ( S AT )
mathematics scores of a random
sample of 500 high school seniors in the
state of Texas are collected, and the
sample mean and standard deviation
are found to be 501 and 112,
respectively. Find a 99% confidence
interval on the mean SAT mathematics
score for seniors in the state of Texas.
Solution

Since the sample size is large, it is

reasonable to use the normal
approximation, z-table will be used.
 he state of Texas are collected, and the sample
Solution
nd to be 501 and 112, respectively. Find a 99%
we find z0.005
T mathematics score=for±2.575.
seniors Hence, a o
in the state
99% confidence interval for μ is
size is large, it is reasonable to use the nor
we find z0.005 = 2.575. Hence, a 99% confide
! "
112
501 ± (2.575) √ = 501 ± 12.9,
500
1 <which
µ < 513.9.
yields 488.1 < μ < 513.9.
Exercise
1. A machine produces metal pieces
that are cylindrical in shape. A sample
of pieces is taken, and the diameters
are found to be 1.01, 0.97, 1.03, 1.04,
0.99, 0.98, 0.99, 1.01, and 1.03
centimeters. Find a 99% con- fidence
interval for the mean diameter of
pieces from this machine, assuming
an approximately normal distribution.
 Solution n = 9, x = 1.005556

( )
n
1
∑ −
2
= 1
2
s x = (0.0048222220
( n − 1) i=1
x i
8
738 Appendix A Statistical Tables and Proofs
S = 0.024552
Table A.4 (continued) Critical Values of the t-Distribution
α
v 0.02 0.015 0.01 0.0075 0.005 0.0025 0.0005
1 15.894 21.205 31.821 42.433 63.656 127.321 636.578
2 4.849 5.643 6.965 8.073 9.925 14.089 31.600
3 3.482 3.896 4.541 5.047 5.841 7.453 12.924
4 2.999 3.298 3.747 4.088 4.604 5.598 8.610
5 2.757 3.003 3.365 3.634 4.032 4.773 6.869
6 2.612 2.829 3.143 3.372 3.707 4.317 5.959
7 2.517 2.715 2.998 3.203 3.499 4.029 5.408
8 2.449 2.634 2.896 3.085 3.355 3.833 5.041
9 2.398 2.574 2.821 2.998 3.250 3.690 4.781
10 2.359 2.527 2.764 2.932 3.169 3.581 4.587
11 2.328 2.491 2.718 2.879 3.106 3.497 4.437
Solution
t0.005 = 3.355 with v = 8 (degrees of
freedom), a 99% confidence
interval for the population mean is

1.0056 − (3.355)(0.0245 / 3) < µ < 1.0056 + (3.355)(0.0245 / 3)

0.978 < µ < 1.033