Dependent Variable: P

Method: Least Squares

Date: 12/11/13 Time: 11:32
Sample: 1/03/1950 12/09/2013
Included observations: 16088

Variable Coefficient Std. Error t-Statistic Prob.

C -307.2818 3.871625 -79.36765 0.0000

@TREND 0.092369 0.000417 221.5926 0.0000

R-squared 0.753242 Mean dependent var 435.6903

Adjusted R-squared 0.753226 S.D. dependent var 494.2939
S.E. of regression 245.5470 Akaike info criterion 13.84498
Sum squared resid 9.70E+08 Schwarz criterion 13.84593
Log likelihood -111367.0 Hannan-Quinn criter. 13.84529
F-statistic 49103.29 Durbin-Watson stat 0.000960
Prob(F-statistic) 0.000000

1.

Uneven Trend

Non-Stationary

Null Hypothesis: P has a unit root

Exogenous: Constant, Linear Trend
Lag Length: 21 (Automatic - based on SIC, maxlag=42)

t-Statistic Prob.*

Augmented Dickey-Fuller test statistic -0.874981 0.9572

Test critical values: 1% level -3.958605
5% level -3.410082
10% level -3.126769

*MacKinnon (1996) one-sided p-values.

Augmented Dickey-Fuller Test Equation

Dependent Variable: D(P)
Method: Least Squares
Date: 12/11/13 Time: 00:16
Sample (adjusted): 2/02/1950 12/09/2013
Included observations: 16066 after adjustments

Variable Coefficient Std. Error t-Statistic Prob.

P(-1) -0.000213 0.000243 -0.874981 0.3816

D(P(-1)) -0.065128 0.007889 -8.255719 0.0000
D(P(-2)) -0.042691 0.007907 -5.399168 0.0000
D(P(-3)) -0.017087 0.007914 -2.159080 0.0309
D(P(-4)) -0.009753 0.007906 -1.233615 0.2174
 D(P(-5)) -0.038168 0.007906 -4.827940 0.0000
D(P(-6)) -0.012548 0.007909 -1.586680 0.1126
D(P(-7)) -0.030904 0.007907 -3.908456 0.0001
D(P(-8)) 0.007349 0.007909 0.929223 0.3528
D(P(-9)) -0.004196 0.007908 -0.530685 0.5956
D(P(-10)) 0.032448 0.007898 4.108179 0.0000
D(P(-11)) -0.011639 0.007902 -1.472910 0.1408
D(P(-12)) 0.048758 0.007900 6.172055 0.0000
D(P(-13)) 0.021209 0.007909 2.681615 0.0073
D(P(-14)) -0.019073 0.007911 -2.410950 0.0159
D(P(-15)) -0.024191 0.007909 -3.058820 0.0022
D(P(-16)) 0.027656 0.007911 3.496115 0.0005
D(P(-17)) 0.018294 0.007908 2.313352 0.0207
D(P(-18)) -0.047570 0.007910 -6.014067 0.0000
D(P(-19)) 0.008477 0.007918 1.070654 0.2843
D(P(-20)) 8.17E-05 0.007911 0.010329 0.9918
D(P(-21)) -0.046335 0.007896 -5.868435 0.0000
C -0.145949 0.140840 -1.036276 0.3001
@TREND(1/03/1950) 4.63E-05 2.59E-05 1.790536 0.0734

R-squared 0.020029 Mean dependent var 0.111498

Adjusted R-squared 0.018624 S.D. dependent var 7.611029
S.E. of regression 7.539821 Akaike info criterion 6.879767
Sum squared resid 911970.1 Schwarz criterion 6.891246
Log likelihood -55241.17 Hannan-Quinn criter. 6.883563
F-statistic 14.25548 Durbin-Watson stat 1.999061
Prob(F-statistic) 0.000000

-29.06799 0.0000
-3.958605
-3.410082
-3.126769

DP(-1) -1.208127 0.041562 -29.06799 0.0000

D(DP(-1)) 0.142840 0.040571 3.520791 0.0004
D(DP(-2)) 0.099996 0.039534 2.529330 0.0114
D(DP(-3)) 0.082756 0.038448 2.152420 0.0314
D(DP(-4)) 0.072855 0.037418 1.947064 0.0515
D(DP(-5)) 0.034538 0.036323 0.950846 0.3417
D(DP(-6)) 0.021837 0.035136 0.621521 0.5343
D(DP(-7)) -0.009215 0.033957 -0.271356 0.7861
D(DP(-8)) -0.002010 0.032778 -0.061307 0.9511
D(DP(-9)) -0.006353 0.031506 -0.201653 0.8402
D(DP(-10)) 0.025942 0.030062 0.862927 0.3882
D(DP(-11)) 0.014150 0.028576 0.495183 0.6205
D(DP(-12)) 0.062754 0.026917 2.331407 0.0197
D(DP(-13)) 0.083808 0.025169 3.329787 0.0009
D(DP(-14)) 0.064577 0.023271 2.774993 0.0055
D(DP(-15)) 0.040232 0.021310 1.887948 0.0591
D(DP(-16)) 0.067737 0.019191 3.529544 0.0004
D(DP(-17)) 0.085886 0.016976 5.059121 0.0000
D(DP(-18)) 0.038172 0.014478 2.636591 0.0084
 D(DP(-19)) 0.046510 0.011535 4.032085 0.0001
D(DP(-20)) 0.046458 0.007894 5.884990 0.0000
C -0.080367 0.119239 -0.674003 0.5003
@TREND(1/03/1950) 2.67E-05 1.29E-05 2.074122 0.0381

R-squared 0.539061 Mean dependent var 0.000204

Adjusted R-squared 0.538429 S.D. dependent var 11.09785
S.E. of regression 7.539766 Akaike info criterion 6.879690
Sum squared resid 912013.7 Schwarz criterion 6.890691
Log likelihood -55241.55 Hannan-Quinn criter. 6.883328
F-statistic 852.8214 Durbin-Watson stat 1.999071
Prob(F-statistic) 0.000000

MA(0) MA(1) MA(2) MA(3)

AR(0)
6.896728 6.892024
6.892565 6.891551

AR(1)
6.892986 6.890907 6.891480 6.892014

AR(2)
6.891824 6.891544 6.891466 6.892653

6.892338

Dependent Variable: DP
Method: Least Squares
Date: 12/11/13 Time: 01:44
Sample (adjusted): 1/05/1950 12/09/2013
Included observations: 16086 after adjustments
Convergence achieved after 8 iterations
MA Backcast: 1/04/1950

Variable Coefficient Std. Error t-Statistic Prob.

C 0.111277 0.049883 2.230768 0.0257

 AR(1) 0.607851 0.056980 10.66776 0.0000
MA(1) -0.672801 0.053089 -12.67311 0.0000

R-squared 0.006645 Mean dependent var 0.111371

Adjusted R-squared 0.006522 S.D. dependent var 7.606298
S.E. of regression 7.581454 Akaike info criterion 6.889474
Sum squared resid 924425.8 Schwarz criterion 6.890907
Log likelihood -55409.04 Hannan-Quinn criter. 6.889948
F-statistic 53.79525 Durbin-Watson stat 2.004706
Prob(F-statistic) 0.000000

Inverted AR Roots .61

Inverted MA Roots .67

Heteroskedasticity Test: ARCH

F-statistic 624.6957 Prob. F(9,16067) 0.0000

Obs*R-squared 4167.458 Prob. Chi-Square(9) 0.0000

Test Equation:
Dependent Variable: RESID^2
Method: Least Squares
Date: 12/11/13 Time: 02:52
Sample (adjusted): 1/18/1950 12/09/2013
Included observations: 16077 after adjustments

Variable Coefficient Std. Error t-Statistic Prob.

C 11.60923 2.045328 5.675975 0.0000

RESID^2(-1) 0.013088 0.007872 1.662714 0.0964
RESID^2(-2) 0.213112 0.007842 27.17408 0.0000
RESID^2(-3) 0.016465 0.007996 2.059229 0.0395
RESID^2(-4) 0.062821 0.007948 7.903630 0.0000
RESID^2(-5) 0.147233 0.007879 18.68761 0.0000
RESID^2(-6) 0.111116 0.007948 13.97978 0.0000
RESID^2(-7) 0.080432 0.007996 10.05965 0.0000
RESID^2(-8) 0.087330 0.007842 11.13558 0.0000
RESID^2(-9) 0.066907 0.007872 8.499328 0.0000

R-squared 0.259219 Mean dependent var 57.49988

Adjusted R-squared 0.258804 S.D. dependent var 286.2004
S.E. of regression 246.3978 Akaike info criterion 13.85239
Sum squared resid 9.75E+08 Schwarz criterion 13.85717
Log likelihood -111342.5 Hannan-Quinn criter. 13.85397
F-statistic 624.6957 Durbin-Watson stat 2.012623
Prob(F-statistic) 0.000000
Breusch-Godfrey Serial Correlation LM Test:

F-statistic 5.950765 Prob. F(5,16078) 0.0000

Obs*R-squared 29.71364 Prob. Chi-Square(5) 0.0000

Test Equation:
Dependent Variable: RESID
Method: Least Squares
Date: 12/11/13 Time: 02:53
Sample: 1/05/1950 12/09/2013
Included observations: 16086
Presample missing value lagged residuals set to zero.

Variable Coefficient Std. Error t-Statistic Prob.

C 1.03E-05 0.049844 0.000207 0.9998

AR(1) -2.043816 0.686427 -2.977469 0.0029
MA(1) 1.126288 0.384924 2.926003 0.0034
RESID(-1) 0.914622 0.306613 2.982983 0.0029
RESID(-2) 0.483687 0.162553 2.975559 0.0029
RESID(-3) 0.260251 0.083179 3.128784 0.0018
RESID(-4) 0.127403 0.040608 3.137390 0.0017
RESID(-5) 0.017538 0.019286 0.909347 0.3632

R-squared 0.001847 Mean dependent var -1.28E-05

Adjusted R-squared 0.001413 S.D. dependent var 7.580983
S.E. of regression 7.575626 Akaike info criterion 6.888246
Sum squared resid 922718.3 Schwarz criterion 6.892069
Log likelihood -55394.17 Hannan-Quinn criter. 6.889510
F-statistic 4.250546 Durbin-Watson stat 2.000390
Prob(F-statistic) 0.000106
Dependent Variable: DP
Method: ML - ARCH (Marquardt) - Normal distribution
Date: 12/11/13 Time: 03:05
Sample (adjusted): 1/05/1950 12/09/2013
Included observations: 16086 after adjustments
Convergence achieved after 32 iterations
MA Backcast: 1/04/1950
Presample variance: backcast (parameter = 0.7)
GARCH = C(4) + C(5)*RESID(-1)^2 + C(6)*GARCH(-1)

Variable Coefficient Std. Error z-Statistic Prob.

C 0.018850 0.003353 5.622112 0.0000

AR(1) -0.141277 0.075434 -1.872843 0.0611
MA(1) 0.242258 0.073980 3.274633 0.0011

Variance Equation

C 0.000213 3.29E-05 6.465720 0.0000

RESID(-1)^2 0.066426 0.001506 44.10476 0.0000
GARCH(-1) 0.939441 0.001222 768.9159 0.0000

R-squared -0.022203 Mean dependent var 0.111371

Adjusted R-squared -0.022330 S.D. dependent var 7.606298
S.E. of regression 7.690752 Akaike info criterion 3.800477
Sum squared resid 951271.9 Schwarz criterion 3.803344
Log likelihood -30561.24 Hannan-Quinn criter. 3.801425
Durbin-Watson stat 2.322505

Inverted AR Roots -.14

Inverted MA Roots -.24
Dependent Variable: DP
Method: ML - ARCH (Marquardt) - Normal distribution
Date: 12/11/13 Time: 03:12
Sample (adjusted): 1/05/1950 12/09/2013
Included observations: 16086 after adjustments
Convergence achieved after 33 iterations
MA Backcast: 1/04/1950
Presample variance: backcast (parameter = 0.7)
GARCH = C(4) + C(5)*RESID(-1)^2 + C(6)*RESID(-2)^2 + C(7)*GARCH(-1)

Variable Coefficient Std. Error z-Statistic Prob.

C 0.019100 0.003404 5.610811 0.0000

AR(1) -0.137936 0.072289 -1.908117 0.0564
MA(1) 0.242221 0.070576 3.432082 0.0006

Variance Equation

C 0.000161 2.62E-05 6.145381 0.0000

RESID(-1)^2 0.107198 0.004442 24.13017 0.0000
RESID(-2)^2 -0.050822 0.005119 -9.928459 0.0000
GARCH(-1) 0.948322 0.001527 621.2227 0.0000

R-squared -0.023299 Mean dependent var 0.111371

Adjusted R-squared -0.023427 S.D. dependent var 7.606298
S.E. of regression 7.694877 Akaike info criterion 3.798666
Sum squared resid 952292.6 Schwarz criterion 3.802010
Log likelihood -30545.67 Hannan-Quinn criter. 3.799772
Durbin-Watson stat 2.328892

Inverted AR Roots -.14

Inverted MA Roots -.24

Dependent Variable: DP
Method: ML - ARCH (Marquardt) - Normal distribution
Date: 12/11/13 Time: 03:19
Sample (adjusted): 1/05/1950 12/09/2013
Included observations: 16086 after adjustments
Convergence achieved after 36 iterations
MA Backcast: 1/04/1950
Presample variance: backcast (parameter = 0.7)
GARCH = C(4) + C(5)*RESID(-1)^2 + C(6)*RESID(-2)^2 + C(7)*GARCH(-1)
+ C(8)*GARCH(-2)

Variable Coefficient Std. Error z-Statistic Prob.

C 0.020273 0.003412 5.940926 0.0000

AR(1) -0.137986 0.072567 -1.901495 0.0572
MA(1) 0.242984 0.070989 3.422855 0.0006

Variance Equation

C 4.30E-06 8.60E-07 5.000378 0.0000

RESID(-1)^2 0.085055 0.002502 34.00018 0.0000
RESID(-2)^2 -0.083594 0.002442 -34.23010 0.0000
GARCH(-1) 1.871332 0.006706 279.0638 0.0000
GARCH(-2) -0.872703 0.006578 -132.6706 0.0000

R-squared -0.023536 Mean dependent var 0.111371

Adjusted R-squared -0.023663 S.D. dependent var 7.606298
S.E. of regression 7.695767 Akaike info criterion 3.794703
Sum squared resid 952512.9 Schwarz criterion 3.798525
Log likelihood -30512.79 Hannan-Quinn criter. 3.795967
Durbin-Watson stat 2.330303

Inverted AR Roots -.14

Inverted MA Roots -.24

GARCH(2,3)

Dependent Variable: DP
Method: ML - ARCH (Marquardt) - Normal distribution
Date: 12/11/13 Time: 12:15
Sample (adjusted): 1/05/1950 12/09/2013
Included observations: 16086 after adjustments
Convergence achieved after 179 iterations
MA Backcast: 1/04/1950
Presample variance: backcast (parameter = 0.7)
GARCH = C(4) + C(5)*RESID(-1)^2 + C(6)*RESID(-2)^2 + C(7)*RESID(-3)^2
+ C(8)*GARCH(-1) + C(9)*GARCH(-2)

Variable Coefficient Std. Error z-Statistic Prob.

C 0.019824 0.003325 5.962788 0.0000

AR(1) -0.142799 0.071582 -1.994902 0.0461
MA(1) 0.248253 0.069856 3.553797 0.0004

Variance Equation

C 1.95E-06 4.27E-07 4.569525 0.0000

RESID(-1)^2 0.103399 0.004377 23.62315 0.0000
RESID(-2)^2 -0.133792 0.009751 -13.72090 0.0000
RESID(-3)^2 0.031082 0.005770 5.386980 0.0000
GARCH(-1) 1.904230 0.005893 323.1577 0.0000
GARCH(-2) -0.904878 0.005823 -155.4076 0.0000

R-squared -0.023694 Mean dependent var 0.111371

Adjusted R-squared -0.023822 S.D. dependent var 7.606298
S.E. of regression 7.696361 Akaike info criterion 3.794321
Sum squared resid 952660.1 Schwarz criterion 3.798621
Log likelihood -30508.72 Hannan-Quinn criter. 3.795743
Durbin-Watson stat 2.331385

Inverted AR Roots -.14

Inverted MA Roots -.25
GARCH (2,2)

Variable Coefficient Std. Error z-Statistic Prob.

C 0.020273 0.003412 5.940926 0.0000

AR(1) -0.137986 0.072567 -1.901495 0.0572
MA(1) 0.242984 0.070989 3.422855 0.0006

Variance Equation

C 4.30E-06 8.60E-07 5.000378 0.0000

RESID(-1)^2 0.085055 0.002502 34.00018 0.0000
RESID(-2)^2 -0.083594 0.002442 -34.23010 0.0000
GARCH(-1) 1.871332 0.006706 279.0638 0.0000
GARCH(-2) -0.872703 0.006578 -132.6706 0.0000

R-squared -0.023536 Mean dependent var 0.111371

Adjusted R-squared -0.023663 S.D. dependent var 7.606298
S.E. of regression 7.695767 Akaike info criterion 3.794703
Sum squared resid 952512.9 Schwarz criterion 3.798525
Log likelihood -30512.79 Hannan-Quinn criter. 3.795967
Durbin-Watson stat 2.330303

Inverted AR Roots -.14

Inverted MA Roots -.24

Dependent Variable: DP
Method: ML - ARCH (Marquardt) - Normal distribution
Date: 12/11/13 Time: 12:23
Sample (adjusted): 1/05/1950 12/09/2013
Included observations: 16086 after adjustments
Convergence achieved after 179 iterations
MA Backcast: 1/04/1950
Presample variance: backcast (parameter = 0.7)
GARCH = C(4) + C(5)*RESID(-1)^2 + C(6)*RESID(-2)^2 + C(7)*RESID(-3)^2
+ C(8)*GARCH(-1) + C(9)*GARCH(-2)

Variable Coefficient Std. Error z-Statistic Prob.

C 0.019824 0.003325 5.962788 0.0000

AR(1) -0.142799 0.071582 -1.994902 0.0461
MA(1) 0.248253 0.069856 3.553797 0.0004

Variance Equation

C 1.95E-06 4.27E-07 4.569525 0.0000

RESID(-1)^2 0.103399 0.004377 23.62315 0.0000
 RESID(-2)^2 -0.133792 0.009751 -13.72090 0.0000
RESID(-3)^2 0.031082 0.005770 5.386980 0.0000
GARCH(-1) 1.904230 0.005893 323.1577 0.0000
GARCH(-2) -0.904878 0.005823 -155.4076 0.0000

R-squared -0.023694 Mean dependent var 0.111371

Adjusted R-squared -0.023822 S.D. dependent var 7.606298
S.E. of regression 7.696361 Akaike info criterion 3.794321
Sum squared resid 952660.1 Schwarz criterion 3.798621
Log likelihood -30508.72 Hannan-Quinn criter. 3.795743
Durbin-Watson stat 2.331385

Inverted AR Roots -.14

Inverted MA Roots -.25