EViews.com

When I run an ARDL model, several coefficients with high probability of insignificance are still included. Is there any way to re-run the ARDL and then select coefficients based on p-value of <.1000?

Not if you want to do the post-estimation cointegration stuff.

If all you're interested in is a true ARDL model, you can re-estimate it as a least squares equation with the lags you want.

Thank you, but on a related note, is there a way I could collect all p-values in a vector with a loop?

Equationname.@pvals

Not if you want to do the post-estimation cointegration stuff.

If all you're interested in is a true ARDL model, you can re-estimate it as a least squares equation with the lags you want.

Hi Gareth,

let'S say I want to remove the regressors to get an AR model, is there a quick wat to do that in the command line? Let's say the ARDL(n,1) model was selected, and I want to create an AR(n) model, without knowing n beforehand.

Thanks!