0% found this document useful (0 votes)
84 views

Unit Root Test October 02

The document reports the results of several unit root tests performed on the natural logarithm of GDP at constant prices (lngdp_con) for India using time series data from 1957 to 2020: 1. Augmented Dickey-Fuller (ADF) and Phillips-Perron (PP) tests with trend and drift terms indicate the presence of a unit root, failing to reject the null hypothesis of a unit root. 2. The DF-GLS test using both information criteria for lag selection and Schwert's criteria for maximum lag length also indicate the presence of a unit root. 3. In conclusion, the various unit root tests show that lngdp_con contains a unit root and

Uploaded by

S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
84 views

Unit Root Test October 02

The document reports the results of several unit root tests performed on the natural logarithm of GDP at constant prices (lngdp_con) for India using time series data from 1957 to 2020: 1. Augmented Dickey-Fuller (ADF) and Phillips-Perron (PP) tests with trend and drift terms indicate the presence of a unit root, failing to reject the null hypothesis of a unit root. 2. The DF-GLS test using both information criteria for lag selection and Schwert's criteria for maximum lag length also indicate the presence of a unit root. 3. In conclusion, the various unit root tests show that lngdp_con contains a unit root and

Uploaded by

S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

Econometric Analysis II Friday October 2 01:37:52 2020 Page 1

___ ____ ____ ____ ____(R)


/__ / ____/ / ____/
___/ / /___/ / /___/
Statistics/Data Analysis

User: Pulak Mishra


Project: Unit Root Test

1 . drop time lngdp_con aps lnaps

2 . generate time=(1)+_n-1 Generating 'time' variable

3 . tsset time, yearly Setting the data as time-series


time variable: time, 1 to 57
delta: 1 year

4 . twoway (line gdp_con time) Plot of 'gdp_con' (GDP at constant price) against time - exponential trend (Graph 1)

5 . generate lngdp_con=ln( gdp_con) Natural logarithm of gdp_con - 'lngdp_con'

6 . twoway (line lngdp_con time) Plot of lngdp_con against time - linear trend with intercept (Graph 2)

7 . varsoc lngdp_con Selection of lag length of lngdp_con


Selection-order criteria
Sample: 5 - 57 Number of obs = 53

lag LL LR df p FPE AIC HQIC SBIC

0 -54.5864 .476983 2.0976 2.11189 2.13477


1 113.342 335.86 1 0.000 .000877 -4.20158 -4.17299 -4.12723
2 115.444 4.2046* 1 0.040 .000841* -4.24318* -4.20029* -4.13165* Optimum lag length
3 116.219 1.5497 1 0.213 .000848 -4.23468 -4.1775 -4.08598
4 116.234 .02916 1 0.864 .000881 -4.1975 -4.12602 -4.01162

Endogenous: lngdp_con
Exogenous: _cons

8 . dfuller lngdp_con, trend regress lags(0) DF test of unit root of lngdp_con with trend and drift

Dickey-Fuller test for unit root Number of obs = 56

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(t) 0.188 -4.137 -3.494 -3.176 Presence of unit root

MacKinnon approximate p-value for Z(t) = 0.9957

D.lngdp_con Coef. Std. Err. t P>|t| [95% Conf. Interval]

lngdp_con
L1. .0087464 .0466119 0.19 0.852 -.0847453 .1022381
_trend .0003221 .002 0.16 0.873 -.0036893 .0043336
_cons -.0808597 .5676482 -0.14 0.887 -1.219418 1.057698

9 . dfuller lngdp_con, trend regress lags(2) ADF test of unit root of lngdp_con with trend and drift

Augmented Dickey-Fuller test for unit root Number of obs = 54

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(t) 1.254 -4.141 -3.496 -3.178 Presence of unit root

MacKinnon approximate p-value for Z(t) = 1.0000


Econometric Analysis II Friday October 2 01:37:53 2020 Page 2

D.lngdp_con Coef. Std. Err. t P>|t| [95% Conf. Interval]

lngdp_con
L1. .0651269 .0519466 1.25 0.216 -.0392637 .1695175
LD. -.3765547 .1540297 -2.44 0.018 -.6860889 -.0670205
L2D. -.2079839 .1494188 -1.39 0.170 -.5082523 .0922845
_trend -.0017526 .0021877 -0.80 0.427 -.006149 .0026437
_cons -.7507407 .6290486 -1.19 0.238 -2.014861 .5133798

10 . pperron lngdp_con, trend regress PP test of unit root of lngdp_con with trend and drift: Newey-West lag selection
criteria
Phillips-Perron test for unit root Number of obs = 56
Newey-West lags = 3

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(rho) 1.903 -25.904 -19.908 -16.884


Z(t) 0.993 -4.137 -3.494 -3.176 Presence of unit root

MacKinnon approximate p-value for Z(t) = 1.0000

lngdp_con Coef. Std. Err. t P>|t| [95% Conf. Interval]

lngdp_con
L1. 1.008746 .0466119 21.64 0.000 .9152547 1.102238
_trend .0003221 .002 0.16 0.873 -.0036893 .0043336
_cons -.0808597 .5676482 -0.14 0.887 -1.219418 1.057698

11 . pperron lngdp_con, lags(2) trend regress


PP test of unit root of lngdp_con with trend and drift: Information criteria
for lag selection
Phillips-Perron test for unit root Number of obs = 56
Newey-West lags = 2

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(rho) 1.778 -25.904 -19.908 -16.884


Z(t) 0.897 -4.137 -3.494 -3.176 Presence of unit root

MacKinnon approximate p-value for Z(t) = 1.0000

lngdp_con Coef. Std. Err. t P>|t| [95% Conf. Interval]

lngdp_con
L1. 1.008746 .0466119 21.64 0.000 .9152547 1.102238
_trend .0003221 .002 0.16 0.873 -.0036893 .0043336
_cons -.0808597 .5676482 -0.14 0.887 -1.219418 1.057698
Econometric Analysis II Friday October 2 01:37:53 2020 Page 3

12 . dfgls lngdp_con, maxlag(2) DF-GLS test of unit root of lngdp_con with trend and drift: Information criteria for lag
selection
DF-GLS for lngdp_con Number of obs = 54

DF-GLS tau 1% Critical 5% Critical 10% Critical


[lags] Test Statistic Value Value Value

2 0.091 -3.743 -3.112 -2.816


1 0.145 -3.743 -3.145 -2.846 Presence of unit root

Opt Lag (Ng-Perron seq t) = 0 [use maxlag(0)]


Min SC = -6.829083 at lag 1 with RMSE .0305494
Min MAIC = -6.938912 at lag 1 with RMSE .0305494

13 . dfgls lngdp_con DF-GLS test of unit root of lngdp_con with trend and drift: Schwert criteria for maxlag length

DF-GLS for lngdp_con Number of obs = 46


Maxlag = 10 chosen by Schwert criterion

DF-GLS tau 1% Critical 5% Critical 10% Critical


[lags] Test Statistic Value Value Value

10 -1.702 -3.743 -2.701 -2.414


9 -1.468 -3.743 -2.754 -2.470
8 -1.251 -3.743 -2.812 -2.528 Presence of unit root
7 -0.678 -3.743 -2.871 -2.587
6 -0.391 -3.743 -2.931 -2.645
5 -0.154 -3.743 -2.991 -2.702
4 -0.027 -3.743 -3.048 -2.756
3 -0.131 -3.743 -3.101 -2.805
2 0.158 -3.743 -3.148 -2.849
1 0.149 -3.743 -3.189 -2.886 Presence of unit root

Opt Lag (Ng-Perron seq t) = 8 with RMSE .0255024


Min SC = -6.760807 at lag 1 with RMSE .0313157
Min MAIC = -6.882696 at lag 1 with RMSE .0313157

14 . generate aps= save_h/ gdp_cur Generating new variable - 'aps' (average propensity to save)
15 . twoway (line aps time) Plot of 'aps' against time - increasing trend with fluctuations (Graph 3)

16 . generate lnaps=ln( aps) Natural logarithm of aps - 'lnaps'

17 . twoway (line lnaps time) Plot of 'lnaps' against time - increasing trend with fluctuations (Graph 4)

18 . varsoc lnaps Selection of lag length for lnaps

Selection-order criteria
Sample: 5 - 57 Number of obs = 53

lag LL LR df p FPE AIC HQIC SBIC

0 -30.3102 .190833 1.18152 1.19581 1.21869


1 39.9094 140.44 1 0.000 .014004 -1.43054 -1.40195 -1.35619
2 40.0306 .24249 1 0.622 .014478 -1.39738 -1.35449 -1.28586
3 43.9015 7.7418* 1 0.005 .012993* -1.50572* -1.44854* -1.35702* Optimum lag length
4 43.9472 .09124 1 0.763 .013474 -1.4697 -1.39822 -1.28383

Endogenous: lnaps
Exogenous: _cons
Econometric Analysis II Friday October 2 01:37:54 2020 Page 4

19 . dfuller lnaps, trend regress lags(0) DF test of unit root of lnaps with trend and drift

Dickey-Fuller test for unit root Number of obs = 56

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(t) -4.389 -4.137 -3.494 -3.176

MacKinnon approximate p-value for Z(t) = 0.0023 No unit root (at 1 percent significance level) - stationary series

D.lnaps Coef. Std. Err. t P>|t| [95% Conf. Interval]

lnaps
L1. -.534121 .1217015 -4.39 0.000 -.7782234 -.2900186
_trend .0147474 .0034717 4.25 0.000 .0077841 .0217106
_cons -1.509179 .3511948 -4.30 0.000 -2.213586 -.804771

20 . dfuller lnaps, trend regress lags(3) ADF test of unit root of lnaps with trend and drift

Augmented Dickey-Fuller test for unit root Number of obs = 53

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(t) -3.747 -4.143 -3.497 -3.178

MacKinnon approximate p-value for Z(t) = 0.0195 No unit root (at 5 percent significance level) - stationary series

D.lnaps Coef. Std. Err. t P>|t| [95% Conf. Interval]

lnaps
L1. -.692485 .1848183 -3.75 0.000 -1.064291 -.3206785
LD. .315087 .1761112 1.79 0.080 -.0392031 .6693772
L2D. -.040907 .1499053 -0.27 0.786 -.3424775 .2606635
L3D. .1764617 .1391399 1.27 0.211 -.1034517 .4563751
_trend .018605 .0051718 3.60 0.001 .0082006 .0290094
_cons -1.957399 .5394094 -3.63 0.001 -3.042551 -.8722477

21 . pperron lnaps, trend regress PP test of unit root of lnaps with trend and drift: Newey-West lag selection criteria

Phillips-Perron test for unit root Number of obs = 56


Newey-West lags = 3

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(rho) -29.343 -25.904 -19.908 -16.884


Z(t) -4.360 -4.137 -3.494 -3.176

MacKinnon approximate p-value for Z(t) = 0.0025 No unit root (at 1 percent significance level) - stationary series
Econometric Analysis II Friday October 2 01:37:54 2020 Page 5

lnaps Coef. Std. Err. t P>|t| [95% Conf. Interval]

lnaps
L1. .465879 .1217015 3.83 0.000 .2217766 .7099814
_trend .0147474 .0034717 4.25 0.000 .0077841 .0217106
_cons -1.509179 .3511948 -4.30 0.000 -2.213586 -.804771

22 . pperron lnaps, lags(3) trend regress PP test of unit root of lnaps with trend and drift: Information criteria

Phillips-Perron test for unit root Number of obs = 56


Newey-West lags = 3

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(rho) -29.343 -25.904 -19.908 -16.884


Z(t) -4.360 -4.137 -3.494 -3.176

MacKinnon approximate p-value for Z(t) = 0.0025 No unit root (at 1 percent significance level) - stationary series

lnaps Coef. Std. Err. t P>|t| [95% Conf. Interval]

lnaps
L1. .465879 .1217015 3.83 0.000 .2217766 .7099814
_trend .0147474 .0034717 4.25 0.000 .0077841 .0217106
_cons -1.509179 .3511948 -4.30 0.000 -2.213586 -.804771

23 . dfgls lnaps, maxlag(3) ers DF-GLS test of unit root of lnaps with trend and drift: Information criteria

DF-GLS for lnaps Number of obs = 53

DF-GLS tau 1% Critical 5% Critical 10% Critical


[lags] Test Statistic Value Value Value

3 -3.855 -3.743 -3.168 -2.869


2 -3.630 -3.743 -3.168 -2.869
-4.803 -3.743 -3.168 -2.869
No unit root
1

Opt Lag (Ng-Perron seq t) = 1 with RMSE .095818 No unit root (at 1/5 percent significance level) - stationary series
Min SC = -4.540787 at lag 1 with RMSE .095818
Min MAIC = -3.630784 at lag 2 with RMSE .095208

24 . dfgls lnaps DF-GLS test of unit root of lnaps with trend and drift: Schwert criteria for lag length

DF-GLS for lnaps Number of obs = 46


Maxlag = 10 chosen by Schwert criterion

DF-GLS tau 1% Critical 5% Critical 10% Critical


[lags] Test Statistic Value Value Value

10 -1.855 -3.743 -2.701 -2.414


9 -1.834 -3.743 -2.754 -2.470
8 -2.502 -3.743 -2.812 -2.528
7 -3.921 -3.743 -2.871 -2.587
6 -3.092 -3.743 -2.931 -2.645
5 -3.153 -3.743 -2.991 -2.702
4 -3.394 -3.743 -3.048 -2.756
3 -3.120 -3.743 -3.101 -2.805
2 -2.890 -3.743 -3.148 -2.849
1 -3.763 -3.743 -3.189 -2.886

Opt Lag (Ng-Perron seq t) = 7 with RMSE .0747268 No unit root (at 1/10 percent significance level) - stationary series
Econometric Analysis II Friday October 2 01:37:55 2020 Page 6

Min SC = -4.791624 at lag 1 with RMSE .0838234


Min MAIC = -4.227629 at lag 2 with RMSE .0830472

25 . generate deflator = gdp_cur/ gdp_con Generating variable deflator (GDP deflator)

26 . generate save-con= save_h/ deflator


invalid syntax
r(198);

27 . generate save_con= save_h/ deflator Generating variable 'save_con' (saving at constant price)

28 . twoway (line save_con time) Plot of 'save_con' against time - exponential trend (Graph 5)

29 . generate lnsave_con=ln( save_con) logarithmic transformation of save_con - 'lnsave_con'


Plot of 'lnsave_con' against time - linear trend (Graph 5a)
30 . varsoc lnsave_con Selection of lag length for lnsave_con

Selection-order criteria
Sample: 5 - 57 Number of obs = 53

lag LL LR df p FPE AIC HQIC SBIC

0 -79.9889 1.24398 3.05619 3.07048 3.09336


1 38.3769 236.73 1 0.000 .014838 -1.37271 -1.34412 -1.29836*
2 38.5978 .44187 1 0.506 .015282 -1.34331 -1.30043 -1.23179
3 41.3526 5.5094* 1 0.019 .014305* -1.40953* -1.35235* -1.26083 Optimum lag length
4 41.796 .88688 1 0.346 .014613 -1.38853 -1.31705 -1.20265

Endogenous: lnsave_con
Exogenous: _cons

31 . dfuller lnsave_con, trend regress lags(0) DF test of unit root of lnsave_con with trend and drift

Dickey-Fuller test for unit root Number of obs = 56

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(t) -3.461 -4.137 -3.494 -3.176

MacKinnon approximate p-value for Z(t) = 0.0437 No unit root (at 5 percent significance level) - stationary series

D.lnsave_con Coef. Std. Err. t P>|t| [95% Conf. Interval]

lnsave_con
L1. -.3801907 .1098402 -3.46 0.001 -.6005022 -.1598792
_trend .0273779 .0077711 3.52 0.001 .011791 .0429648
_cons 3.588889 1.021951 3.51 0.001 1.539115 5.638664

32 . dfuller lnsave_con, trend regress lags(3) ADF test of unit root of lnsave_con with trend and drift

Augmented Dickey-Fuller test for unit root Number of obs = 53

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(t) -2.157 -4.143 -3.497 -3.178

MacKinnon approximate p-value for Z(t) = 0.5143 Presence of unit root - non-stationary series
Econometric Analysis II Friday October 2 01:37:55 2020 Page 7

D.lnsave_con Coef. Std. Err. t P>|t| [95% Conf. Interval]

lnsave_con
L1. -.3474527 .1611097 -2.16 0.036 -.6715637 -.0233418
LD. .0771822 .1769877 0.44 0.665 -.2788712 .4332355
L2D. -.1480655 .1569427 -0.94 0.350 -.4637935 .1676626
L3D. .0063329 .1489727 0.04 0.966 -.2933614 .3060273
_trend .0249155 .0112901 2.21 0.032 .0022027 .0476282
_cons 3.295281 1.481789 2.22 0.031 .3143068 6.276256

33 . pperron lngdp_con, trend regress PP test of unit root of lnsave_con with trend and drift: Newey-West criteria for lag
length
Phillips-Perron test for unit root Number of obs = 56
Newey-West lags = 3

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(rho) 1.903 -25.904 -19.908 -16.884


Z(t) 0.993 -4.137 -3.494 -3.176

MacKinnon approximate p-value for Z(t) = 1.0000 Presence of unit root - non-stationary series

lngdp_con Coef. Std. Err. t P>|t| [95% Conf. Interval]

lngdp_con
L1. 1.008746 .0466119 21.64 0.000 .9152547 1.102238
_trend .0003221 .002 0.16 0.873 -.0036893 .0043336
_cons -.0808597 .5676482 -0.14 0.887 -1.219418 1.057698

34 . pperron lngdp_con, lags(3) trend regress PP test of unit root of lnsave_con with trend and drift: Information criteria
for lag selection
Phillips-Perron test for unit root Number of obs = 56
Newey-West lags = 3

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(rho) 1.903 -25.904 -19.908 -16.884


Z(t) 0.993 -4.137 -3.494 -3.176

MacKinnon approximate p-value for Z(t) = 1.0000 Presence of unit root - non-stationary series

lngdp_con Coef. Std. Err. t P>|t| [95% Conf. Interval]

lngdp_con
L1. 1.008746 .0466119 21.64 0.000 .9152547 1.102238
_trend .0003221 .002 0.16 0.873 -.0036893 .0043336
_cons -.0808597 .5676482 -0.14 0.887 -1.219418 1.057698
Econometric Analysis II Friday October 2 01:37:56 2020 Page 8

35 . dfgls gdp_con, maxlag(3) ers DF-GLS test of unit root of lnsave_cons with trend and drift: Information criteria for lag
selection
DF-GLS for gdp_con Number of obs = 53

DF-GLS tau 1% Critical 5% Critical 10% Critical


[lags] Test Statistic Value Value Value

3 -0.231 -3.743 -3.168 -2.869


2 -0.054 -3.743 -3.168 -2.869
1 0.376 -3.743 -3.168 -2.869

Opt Lag (Ng-Perron seq t) = 2 with RMSE 27104.99 Presence of unit root - non-stationary series
Min SC = 20.63968 at lag 2 with RMSE 27104.99
Min MAIC = 20.47533 at lag 3 with RMSE 26364.65

36 . dfgls gdp_con DF-GLS test of unit root of lnsave_cons with trend and drift: Schwert criteria for lag selection

DF-GLS for gdp_con Number of obs = 46


Maxlag = 10 chosen by Schwert criterion

DF-GLS tau 1% Critical 5% Critical 10% Critical


[lags] Test Statistic Value Value Value

10 -0.936 -3.743 -2.701 -2.414


9 -0.904 -3.743 -2.754 -2.470
8 -1.300 -3.743 -2.812 -2.528
7 -1.198 -3.743 -2.871 -2.587
6 -0.887 -3.743 -2.931 -2.645
5 -0.681 -3.743 -2.991 -2.702
4 -0.365 -3.743 -3.048 -2.756
3 -0.396 -3.743 -3.101 -2.805
2 -0.145 -3.743 -3.148 -2.849
1 0.359 -3.743 -3.189 -2.886

Opt Lag (Ng-Perron seq t) = 3 with RMSE 27819.47 Presence of unit root - non-stationary series
Min SC = 20.78441 at lag 2 with RMSE 28777.69
Min MAIC = 20.60655 at lag 3 with RMSE 27819.47

37 . reg lnsave_con lngdp_con Test for cointegration between two non-stationary series - lnsave_con and lngdp_con

Source SS df MS Number of obs = 57


F( 1, 55) = 4402.17
Model 77.1001849 1 77.1001849 Prob > F = 0.0000
Residual .963277274 55 .017514132 R-squared = 0.9877
Adj R-squared = 0.9874
Total 78.0634622 56 1.3939904 Root MSE = .13234

lnsave_con Coef. Std. Err. t P>|t| [95% Conf. Interval]

lngdp_con 1.628394 .0245429 66.35 0.000 1.579209 1.677579


_cons -10.50616 .3297599 -31.86 0.000 -11.16702 -9.84531

OLS regression of lnsave_con on lngdp_con


38 . predict u, res Prediction of residual - u
Econometric Analysis II Friday October 2 01:37:56 2020 Page 9

39 . estat dwatson

Durbin-Watson d-statistic( 2, 57) = .8150855 DW > 0.511 (Critical value at 1 percent suggested
by Sargan and Bhargava)
40 . varsoc u Selection of lag length for u
Rejection of null hypothesis - lnsave_con and lngdp_con are cointegrated
Selection-order criteria
Sample: 5 - 57 Number of obs = 53

lag LL LR df p FPE AIC HQIC SBIC

0 33.5723 .017128 -1.22914 -1.21485 -1.19197


1 43.998 20.851* 1 0.000 .012002* -1.58483* -1.55624* -1.51048*
2 44.7179 1.4399 1 0.230 .012131 -1.57426 -1.53137 -1.46273
3 45.9676 2.4994 1 0.114 .012019 -1.58368 -1.5265 -1.43498
4 46.5664 1.1975 1 0.274 .012206 -1.56854 -1.49706 -1.38267

Endogenous: u
Exogenous: _cons

41 . twoway (line u time) Plot of 'u' against time - fluctuations around the horizontal axis (zero) - Graph 6

42 . dfuller u, regress lags(0) DF test of unit root of u with drift (??)

Dickey-Fuller test for unit root Number of obs = 56

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(t) -3.617 -3.572 -2.925 -2.598

MacKinnon approximate p-value for Z(t) = 0.0054 No unit root (significance at 1 percent level) - stationary series

D.u Coef. Std. Err. t P>|t| [95% Conf. Interval]

u
L1. -.4059453 .1122186 -3.62 0.001 -.63093 -.1809606

_cons -.0008783 .0144588 -0.06 0.952 -.0298664 .0281099

43 . dfuller u, regress lags(1) ADF test of unit root of u with drift (??)
Augmented Dickey-Fuller test for unit root Number of obs = 55

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(t) -3.735 -3.573 -2.926 -2.598

MacKinnon approximate p-value for Z(t) = 0.0037 No unit root (significance - stationary series

D.u Coef. Std. Err. t P>|t| [95% Conf. Interval]

u
L1. -.4705449 .1259928 -3.73 0.000 -.723368 -.2177218
LD. .1273402 .1372496 0.93 0.358 -.1480712 .4027517

_cons .0022327 .0144867 0.15 0.878 -.0268369 .0313023


Econometric Analysis II Friday October 2 01:37:56 2020 Page 10

44 . pperron u, regress PP test of unit root of u with drift (??): Newey-West criteria for lag length

Phillips-Perron test for unit root Number of obs = 56


Newey-West lags = 3

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(rho) -21.946 -19.008 -13.348 -10.736


Z(t) -3.564 -3.572 -2.925 -2.598

MacKinnon approximate p-value for Z(t) = 0.0065 No unit root - stationary series

u Coef. Std. Err. t P>|t| [95% Conf. Interval]

u
L1. .5940547 .1122186 5.29 0.000 .36907 .8190394

_cons -.0008783 .0144588 -0.06 0.952 -.0298664 .0281099

45 . pperron u, regress lags(1) PP test of unit root of u with drift (??): Information criteria for lag length selection

Phillips-Perron test for unit root Number of obs = 56


Newey-West lags = 1

Interpolated Dickey-Fuller
Test 1% Critical 5% Critical 10% Critical
Statistic Value Value Value

Z(rho) -23.947 -19.008 -13.348 -10.736


Z(t) -3.698 -3.572 -2.925 -2.598

MacKinnon approximate p-value for Z(t) = 0.0041 No unit root - stationary series

u Coef. Std. Err. t P>|t| [95% Conf. Interval]

u
L1. .5940547 .1122186 5.29 0.000 .36907 .8190394

_cons -.0008783 .0144588 -0.06 0.952 -.0298664 .0281099

46 . dfgls u, notrend maxlag(3) DF-GLS test of unit root of u with drift (??): Information criteria for lag length selection

DF-GLS for u Number of obs = 53

DF-GLS mu 1% Critical 5% Critical 10% Critical


[lags] Test Statistic Value Value Value

3 -2.607 -2.617 -2.188 -1.889


2 -2.474 -2.617 -2.210 -1.910
1 -3.509 -2.617 -2.231 -1.929

Opt Lag (Ng-Perron seq t) = 2 with RMSE .1032495 No unit root (at 1/5 percent significance level) - stationary series
Min SC = -4.32893 at lag 1 with RMSE .1065249
Min MAIC = -4.095177 at lag 2 with RMSE .1032495
Econometric Analysis II Friday October 2 01:37:57 2020 Page 11

47 . dfgls u, notrend maxlag(1) To be ignored


DF-GLS for u Number of obs = 55

DF-GLS mu 1% Critical 5% Critical 10% Critical


[lags] Test Statistic Value Value Value

1 -3.464 -2.617 -2.222 -1.920

48 . dfgls u, notrend maxlag(1) To be ignored


DF-GLS for u Number of obs = 55

DF-GLS mu 1% Critical 5% Critical 10% Critical


[lags] Test Statistic Value Value Value

1 -3.464 -2.617 -2.222 -1.920

49 . dfgls u, notrend DF-GLS test of unit root of u with drift (??): Schwert criteria for lag length selection

DF-GLS for u Number of obs = 46


Maxlag = 10 chosen by Schwert criterion

DF-GLS mu 1% Critical 5% Critical 10% Critical


[lags] Test Statistic Value Value Value

10 -0.922 -2.617 -2.038 -1.735


9 -0.834 -2.617 -2.054 -1.755
8 -1.150 -2.617 -2.075 -1.778
7 -1.767 -2.617 -2.100 -1.805
6 -1.581 -2.617 -2.128 -1.833
5 -1.683 -2.617 -2.157 -1.862
4 -1.960 -2.617 -2.187 -1.890
3 -2.000 -2.617 -2.216 -1.918
2 -1.777 -2.617 -2.243 -1.943
1 -2.621 -2.617 -2.267 -1.965

Opt Lag (Ng-Perron seq t) = 8 with RMSE .081157 Presence of unit root - non-stationary series
Min SC = -4.588458 at lag 2 with RMSE .0890038
Min MAIC = -4.612384 at lag 9 with RMSE .0783415

50 .Most of the tests (except DF-GLS with Schwert criteria) suggest that u does not have unit root and hence it is stationary. This implies
that 'lnsave_con' and 'lngdp_con' are cointegrated indicating a long run relationship between the two. The Durbin-Watson d statistic
also suggests that these two variables are cointegrated. The conclusions are consistent across the two tests (ADF and DW) of
cointegration.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy