0% found this document useful (0 votes)
35 views8 pages

Result For Eq2

The document reports the results of an autoregressive distributed lag (ARDL) model with the natural log of nominal gross national savings (LGNS) as the dependent variable. The optimal model was found to be ARDL(2, 2, 2, 2, 2, 2) including lags of LGNS, the log of real exchange rate (LCEX), the log of real gross national disposable income (LGNDI), inflation (INF), the interest rate differential (DIR), and the log of the real price of energy (LPREM) as regressors. The long-run coefficients were statistically significant for most variables. Diagnostic tests showed no evidence of serial correlation or heteroskedasticity.

Uploaded by

Lema Asnakew
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
35 views8 pages

Result For Eq2

The document reports the results of an autoregressive distributed lag (ARDL) model with the natural log of nominal gross national savings (LGNS) as the dependent variable. The optimal model was found to be ARDL(2, 2, 2, 2, 2, 2) including lags of LGNS, the log of real exchange rate (LCEX), the log of real gross national disposable income (LGNDI), inflation (INF), the interest rate differential (DIR), and the log of the real price of energy (LPREM) as regressors. The long-run coefficients were statistically significant for most variables. Diagnostic tests showed no evidence of serial correlation or heteroskedasticity.

Uploaded by

Lema Asnakew
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 8

Dependent Variable: LGNS

Method: ARDL
Date: 03/15/24 Time: 22:39
Sample (adjusted): 2000 2022
Included observations: 23 after adjustments
Maximum dependent lags: 2 (Automatic selection)
Model selection method: Akaike info criterion (AIC)
Dynamic regressors (2 lags, automatic): LCEX LGNDI INF DIR LPREM
Fixed regressors: C
Number of models evaluated: 486
Selected Model: ARDL(2, 2, 2, 2, 2, 2)

Variable Coefficient Std. Error t-Statistic Prob.*

LGNS(-1) -0.069521 0.112390 -0.618568 0.5633


LGNS(-2) -0.564256 0.131887 -4.278325 0.0079
LCEX -3.543006 0.129124 -27.43874 0.0000
LCEX(-1) -0.125728 0.379909 -0.330944 0.7541
LCEX(-2) -2.098230 0.448698 -4.676259 0.0055
LGNDI 4.839324 0.190691 25.37784 0.0000
LGNDI(-1) 0.237424 0.539043 0.440455 0.6780
LGNDI(-2) 2.358117 0.541658 4.353514 0.0073
INF -0.179592 0.049943 -3.595919 0.0156
INF(-1) -0.064249 0.056817 -1.130816 0.3094
INF(-2) 0.020979 0.020595 1.018643 0.3551
DIR -2.292178 0.628075 -3.649530 0.0148
DIR(-1) -0.083562 0.315560 -0.264806 0.8017
DIR(-2) 1.195022 0.491136 2.433179 0.0591
LPREM 0.006006 0.006342 0.947106 0.3871
LPREM(-1) -0.015427 0.009727 -1.585994 0.1736
LPREM(-2) -0.024316 0.004625 -5.257996 0.0033
C -4.150384 0.596920 -6.952994 0.0009

R-squared 0.999997 Mean dependent var 11.82248


Adjusted R-squared 0.999988 S.D. dependent var 1.564817
S.E. of regression 0.005359 Akaike info criterion -7.581014
Sum squared resid 0.000144 Schwarz criterion -6.692366
Log likelihood 105.1817 Hannan-Quinn criter. -7.357521
F-statistic 110350.4 Durbin-Watson stat 2.818845
Prob(F-statistic) 0.000000

*Note: p-values and any subsequent tests do not account for model
selection.
6
Series: Residuals
Sample 2000 2022
5
Observations 23

4 Mean 2.59e-15
Median -0.000372
3 Maximum 0.005228
Minimum -0.005111
2 Std. Dev. 0.002555
Skewness 0.452336
1 Kurtosis 2.749195

Jarque-Bera 0.844614
0 Probability 0.655533
-0.006 -0.004 -0.002 0.000 0.002 0.004 0.006
Breusch-Godfrey Serial Correlation LM Test:
Null hypothesis: No serial correlation at up to 2 lags

F-statistic 4.757343 Prob. F(2,3) 0.1174


Obs*R-squared 17.48648 Prob. Chi-Square(2) 0.0002

Test Equation:
Dependent Variable: RESID
Method: ARDL
Date: 03/15/24 Time: 22:45
Sample: 2000 2022
Included observations: 23
Presample missing value lagged residuals set to zero.

Variable Coefficient Std. Error t-Statistic Prob.

LGNS(-1) 0.079885 0.078137 1.022374 0.3819


LGNS(-2) 0.025806 0.152753 0.168936 0.8766
LCEX 0.123859 0.093391 1.326246 0.2767
LCEX(-1) 0.218465 0.260381 0.839019 0.4630
LCEX(-2) 0.151375 0.507787 0.298108 0.7851
LGNDI -0.198794 0.154598 -1.285874 0.2887
LGNDI(-1) -0.404068 0.371383 -1.088007 0.3562
LGNDI(-2) -0.006862 0.621050 -0.011048 0.9919
INF 0.100020 0.045799 2.183883 0.1169
INF(-1) 0.090237 0.057088 1.580666 0.2121
INF(-2) -0.004205 0.013293 -0.316373 0.7725
DIR 0.448293 0.472424 0.948921 0.4127
DIR(-1) -0.023636 0.221288 -0.106812 0.9217
DIR(-2) -0.408975 0.413770 -0.988411 0.3958
LPREM -0.003174 0.006661 -0.476534 0.6663
LPREM(-1) 0.008190 0.010629 0.770565 0.4971
LPREM(-2) 0.005782 0.004955 1.166946 0.3276
C 0.360334 0.541198 0.665807 0.5532
RESID(-1) -1.741114 0.566004 -3.076149 0.0543
RESID(-2) -0.450832 1.112842 -0.405118 0.7125

R-squared 0.760282 Mean dependent var 2.59E-15


Adjusted R-squared -0.757935 S.D. dependent var 0.002555
S.E. of regression 0.003387 Akaike info criterion -8.835391
Sum squared resid 3.44E-05 Schwarz criterion -7.848005
Log likelihood 121.6070 Hannan-Quinn criter. -8.587066
F-statistic 0.500773 Durbin-Watson stat 1.836679
Prob(F-statistic) 0.851360
Heteroskedasticity Test: Breusch-Pagan-Godfrey
Null hypothesis: Homoskedasticity

F-statistic 0.992268 Prob. F(17,5) 0.5569


Obs*R-squared 17.74131 Prob. Chi-Square(17) 0.4053
Scaled explained SS 0.733294 Prob. Chi-Square(17) 1.0000

Test Equation:
Dependent Variable: RESID^2
Method: Least Squares
Date: 03/15/24 Time: 22:48
Sample: 2000 2022
Included observations: 23

Variable Coefficient Std. Error t-Statistic Prob.

C -0.000613 0.000943 -0.650383 0.5441


LGNS(-1) -8.11E-06 0.000178 -0.045673 0.9653
LGNS(-2) -0.000252 0.000208 -1.207731 0.2812
LCEX 0.000145 0.000204 0.708389 0.5104
LCEX(-1) -0.000286 0.000600 -0.477158 0.6534
LCEX(-2) -0.000806 0.000709 -1.136867 0.3071
LGNDI 5.16E-05 0.000301 0.171198 0.8708
LGNDI(-1) -8.47E-06 0.000852 -0.009940 0.9925
LGNDI(-2) 0.001163 0.000856 1.358928 0.2323
INF -6.43E-05 7.89E-05 -0.815433 0.4519
INF(-1) 8.81E-05 8.98E-05 0.981200 0.3716
INF(-2) 2.82E-06 3.25E-05 0.086560 0.9344
DIR -0.000129 0.000992 -0.129737 0.9018
DIR(-1) -0.000658 0.000499 -1.320319 0.2439
DIR(-2) 0.000501 0.000776 0.645428 0.5471
LPREM -3.10E-06 1.00E-05 -0.309161 0.7697
LPREM(-1) -1.11E-06 1.54E-05 -0.072297 0.9452
LPREM(-2) 3.74E-06 7.31E-06 0.511191 0.6310

R-squared 0.771361 Mean dependent var 6.24E-06


Adjusted R-squared -0.006010 S.D. dependent var 8.44E-06
S.E. of regression 8.47E-06 Akaike info criterion -20.48158
Sum squared resid 3.58E-10 Schwarz criterion -19.59293
Log likelihood 253.5382 Hannan-Quinn criter. -20.25809
F-statistic 0.992268 Durbin-Watson stat 3.167369
Prob(F-statistic) 0.556922
8
6
4
2
0
-2
-4
-6
-8
2018 2019 2020 2021 2022

CUSUM 5% Significance

1.6

1.2

0.8

0.4

0.0

-0.4
2018 2019 2020 2021 2022

CUSUM of Square s 5% Significance


ARDL Long Run Form and Bounds Test
Dependent Variable: D(LGNS)
Selected Model: ARDL(2, 2, 2, 2, 2, 2)
Case 3: Unrestricted Constant and No Trend
Date: 03/15/24 Time: 22:58
Sample: 1998 2022
Included observations: 23

Conditional Error Correction Regression

Variable Coefficient Std. Error t-Statistic Prob.

C -4.150384 0.596920 -6.952994 0.0009


LGNS(-1)* -1.633776 0.221429 -7.378335 0.0007
LCEX(-1) -5.766965 0.792066 -7.280918 0.0008
LGNDI(-1) 7.434865 1.019158 7.295108 0.0008
INF(-1) -0.222863 0.087289 -2.553143 0.0511
DIR(-1) -1.180719 0.487334 -2.422812 0.0599
LPREM(-1) -0.033738 0.008757 -3.852475 0.0120
D(LGNS(-1)) 0.564256 0.131887 4.278325 0.0079
D(LCEX) -3.543006 0.129124 -27.43875 0.0000
D(LCEX(-1)) 2.098230 0.448698 4.676259 0.0055
D(LGNDI) 4.839324 0.190691 25.37784 0.0000
D(LGNDI(-1)) -2.358117 0.541658 -4.353514 0.0073
D(INF) -0.179592 0.049943 -3.595919 0.0156
D(INF(-1)) -0.020979 0.020595 -1.018643 0.3551
D(DIR) -2.292178 0.628075 -3.649530 0.0148
D(DIR(-1)) -1.195022 0.491136 -2.433179 0.0591
D(LPREM) 0.006006 0.006342 0.947106 0.3871
D(LPREM(-1)) 0.024316 0.004625 5.257996 0.0033

* p-value incompatible with t-Bounds distribution.

Levels Equation
Case 3: Unrestricted Constant and No Trend

Variable Coefficient Std. Error t-Statistic Prob.

LCEX -3.529837 0.076384 -46.21203 0.0000


LGNDI 4.550724 0.077015 59.08868 0.0000
INF -0.136409 0.046514 -2.932651 0.0325
DIR -0.722693 0.235853 -3.064166 0.0280
LPREM -0.020650 0.004346 -4.751966 0.0051

EC = LGNS - (-3.5298*LCEX + 4.5507*LGNDI -0.1364*INF -0.7227*DIR


-0.0207*LPREM)

F-Bounds Test Null Hypothesis: No levels relationship

Test Statistic Value Signif. I(0) I(1)

Asymptotic: n=1000
F-statistic 29.50407 10% 2.26 3.35
k 5 5% 2.62 3.79
2.5% 2.96 4.18
1% 3.41 4.68

Actual Sample Size 23 Finite Sample: n=35


10% 2.508 3.763
5% 3.037 4.443
1% 4.257 6.04
ARDL Error Correction Regression
Dependent Variable: D(LGNS)
Selected Model: ARDL(2, 2, 2, 2, 2, 2)
Case 3: Unrestricted Constant and No Trend
Date: 03/15/24 Time: 22:59
Sample: 1998 2022
Included observations: 23

ECM Regression
Case 3: Unrestricted Constant and No Trend

Variable Coefficient Std. Error t-Statistic Prob.

C -4.150384 0.223315 -18.58531 0.0000


D(LGNS(-1)) 0.564256 0.054206 10.40945 0.0001
D(LCEX) -3.543006 0.034318 -103.2398 0.0000
D(LCEX(-1)) 2.098230 0.180847 11.60224 0.0001
D(LGNDI) 4.839324 0.057406 84.30007 0.0000
D(LGNDI(-1)) -2.358117 0.222839 -10.58217 0.0001
D(INF) -0.179592 0.016842 -10.66327 0.0001
D(INF(-1)) -0.020979 0.010892 -1.926130 0.1120
D(DIR) -2.292178 0.185060 -12.38614 0.0001
D(DIR(-1)) -1.195022 0.197643 -6.046375 0.0018
D(LPREM) 0.006006 0.002980 2.015753 0.0999
D(LPREM(-1)) 0.024316 0.002324 10.46112 0.0001
CointEq(-1)* -1.633776 0.086828 -18.81619 0.0000

R-squared 0.999663 Mean dependent var 0.219958


Adjusted R-squared 0.999260 S.D. dependent var 0.139256
S.E. of regression 0.003789 Akaike info criterion -8.015796
Sum squared resid 0.000144 Schwarz criterion -7.373995
Log likelihood 105.1817 Hannan-Quinn criter. -7.854385
F-statistic 2475.290 Durbin-Watson stat 2.818845
Prob(F-statistic) 0.000000

* p-value incompatible with t-Bounds distribution.

F-Bounds Test Null Hypothesis: No levels relationship

Test Statistic Value Signif. I(0) I(1)

F-statistic 29.50407 10% 2.26 3.35


k 5 5% 2.62 3.79
2.5% 2.96 4.18
1% 3.41 4.68

t-Bounds Test Null Hypothesis: No levels relationship

Test Statistic Value Signif. I(0) I(1)

t-statistic -18.81619 10% -2.57 -3.86


5% -2.86 -4.19
2.5% -3.13 -4.46
1% -3.43 -4.79

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