Page 1 of 1

Newey-West Standard Errors and Hansen-Hodrick Standard Error

Posted: Tue Jul 02, 2013 7:22 am
by code8
Hi

I want to know if two data series are different from each other. However, due to the nature of the data there is auto correlation of 11 lags.
I want to obtain the t statistics and the p-values that uses Newey-West standard errors and another set of t statistics and p-values using hansen-hodrick standard errors.
My regression is a simple OLS regression. Since I am new to Eviews, I am not sure how to do this. :D Can anyone help me out?

Thank you for your time.

Re: Newey-West Standard Errors and Hansen-Hodrick Standard E

Posted: Tue Jul 02, 2013 10:31 am
by EViews Glenn
On the options tab of the equation estimation dialog there are settings for the "Coefficient covariance matrix". Select "HAC (Newey-West)" from the combo. The truncated uniform kernel is used for Hansen-Hodrick. Newey-West use the Bartlett kernel. You can choose your bandwith method as desired.