Hello.

I want to know the causality between GDP and Employment.( I have two time series data: GDP and employment)

I am using varsoc command and my stata command is:

1. varsoc gdp employment
2. varsoc employment gdp

So my question is that, is there any need to find a optimal lag length after using varsoc gdp employment?

Can it be different lags for each direction?

For example: Lag 2 for GDP and employment
Lag 3 for employment and GDP


My second question is that:

When I use the 'forvalues' command, it gives a different lag length with each variable.

For example, Y → X (lag 2, based on AIC), X → Y (lag 3).

In my understanding, with each direction(Y → X, X →Y), the lag length should be the same.

Is it okay to use the command of 'varsoc'? Is it different than the command of 'forvalues?

Thanks a lot.