As we have learned in previous posts, that, causality defines the relationship between two variables. In this section, we will test the relationship between two unidirectional variable by using Granger causality test in Eviews and then we will study the interpretation of the output generated in Eview.
To investigate the causal relationship between two variables with the help of granger causality test eviews you need to follow below steps:
1. Open Eviews6.exe
2. Click on File -> Open -> Foreign Data as Workfile…
3. Open the data file “broadband_1 “ by selecting through the path C:\Program Files\SPSSInc\Statistics17\Samples\English
4. Select MARKET_1 and MARKET_2 -> OK
5. Click on Quick -> Group Statistics -> Ganger Causality Test
6. Write down the dependent variables followed by independent variables and then click OK:
7. Select lags to include = 2 and then click OK:
8. Following output will be displayed:
Interpretation of Granger causality test Eviews
Two null hypotheses are being displayed in the above output.
If F ≥ 3.84 then H (A) (Alternate hypothesis is accepted)
If F < 3.84 then H (o) (Null hypothesis is accepted)
For the null hypothesis 1, in the above figure F ≥ 3.84, therefore Alternate hypothesis is going to be accepted which means MARKET_2 Causes MARKET_1.
Whereas, for the null hypothesis 2, in the above figure F < 3.84, therefore null hypothesis is going to be accepted which means MARKET_1 does not Causes MARKET_2.
Hence this proves that the above cause and effect relationship is unidirectional and not bidirectional.
For further details click here granger causality test eviews.