Scribd
Upload
193 views2 pages

Granger Causality Test-EAI

The document uses data from India to test for Granger causality between the variables "savecons" and "gdpcons" using a vector autoregression model. It finds that lags of "savecons" help predict "gdpcons" but lags of "gdpcons" do not help predict "savecons", indicating a causal relationship running from "savecons" to "gdpcons" but not vice versa. The analysis provides evidence that savings causes changes in GDP consumption in India based on the dataset from 1963 to 2015.

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
193 views2 pages

Granger Causality Test-EAI

The document uses data from India to test for Granger causality between the variables "savecons" and "gdpcons" using a vector autoregression model. It finds that lags of "savecons" help predict "gdpcons" but lags of "gdpcons" do not help predict "savecons", indicating a causal relationship running from "savecons" to "gdpcons" but not vice versa. The analysis provides evidence that savings causes changes in GDP consumption in India based on the dataset from 1963 to 2015.

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

Granger Causality Test Saturday May 2 20:18:42 2020 Page 1

___ ____ ____ ____ ____(R)


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

User: Pulak Mishra


Project: Econometric Analysis-I

1 . tsset time, yearly Setting the dataset as 'time-series'


time variable: time, 1 to 63
delta: 1 year

2 . varsoc savecons, maxlag(4) Selection of lag length of 'savecons'


Maximum lag length(4) is selected as the nearest integer of 4*(n/100)^(2/9)
Selection-order criteria
Sample: 5 - 63 Number of obs = 59

lag LL LR df p FPE AIC HQIC SBIC

0 -585.813 2.5e+07 19.892 19.9057 19.9272


1 -464.187 243.25 1 0.000 427232* 15.8029* 15.8304* 15.8734*
2 -464.114 .14487 1 0.703 440906 15.8344 15.8756 15.94
3 -463.688 .85124 1 0.356 449629 15.8538 15.9088 15.9947
4 -461.652 4.0725* 1 0.044 434195 15.8187 15.8874 15.9948

Endogenous: savecons
Exogenous: _cons

3 . varsoc gdpcons, maxlag(4) Selection of lag length of 'gdpcons'


Maximum lag length (4) is selected as the nearest integer of 4*(n/100)^(2/9)
Selection-order criteria
Sample: 5 - 63 Number of obs = 59

lag LL LR df p FPE AIC HQIC SBIC

0 -644.723 1.9e+08 21.8889 21.9027 21.9241


1 -434.074 421.3* 1 0.000 153943* 14.7822* 14.8097* 14.8526*
2 -433.094 1.9609 1 0.161 154054 14.7828 14.8241 14.8885
3 -432.817 .55368 1 0.457 157896 14.8074 14.8623 14.9482
4 -432.797 .04061 1 0.840 163261 14.8406 14.9093 15.0166

Endogenous: gdpcons
Exogenous: _cons

4 . var savecons gdpcons, lags(1) dfk small

Vector autoregression

Sample: 2 - 63 No. of obs = 62


Log likelihood = -908.6832 AIC = 29.50591
FPE = 2.24e+10 HQIC = 29.58673
Det(Sigma_ml) = 1.84e+10 SBIC = 29.71176

Equation Parms RMSE R-sq F P > F

savecons 3 624.181 0.9847 1893.199 0.0000


gdpcons 3 354.576 0.9993 44241.91 0.0000

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

savecons
savecons
L1. .8898377 .1211259 7.35 0.000 .6474653 1.13221

gdpcons
L1. .0573681 .0456688 1.26 0.214 -.034015 .1487511

_cons -115.5422 201.5416 -0.57 0.569 -518.8259 287.7416

gdpcons
savecons
L1. .2044504 .0688075 2.97 0.004 .0667668 .3421339
Granger Causality Test Saturday May 2 20:18:43 2020 Page 2

gdpcons
L1. 1.001158 .0259429 38.59 0.000 .9492462 1.053069

_cons 60.01874 114.489 0.52 0.602 -169.0731 289.1106

5 . vargranger

Granger causality Wald tests

Equation Excluded F df df_r Prob > F As the restricted F-statistic


is NOT significant, 'gdpcons'
savecons gdpcons 1.578 1 59 0.2140 does NOT Granger cause
savecons ALL 1.578 1 59 0.2140 'savecons'.

gdpcons savecons 8.8288 1 59 0.0043 Statistically significant


gdpcons ALL 8.8288 1 59 0.0043 restricted F-statistic
indicates that 'savecons'
Granger causes 'gdpcons'
6 .

You might also like