0
$\begingroup$

I am estimating a VAR model line by line.

Lets say the conditional variances are correlated.

We would expect size distortion. So we would use another method, perhaps a HAC standard error to account for the conditional heteroskedasticity.

My question is, how would the estimation of the first line the error term from the second equation (and hence the correlation) into account.

$\endgroup$
  • $\begingroup$ I would post this in Cross Validated, the Stats SE. $\endgroup$ – David Apr 17 at 11:46

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.