Re: st: -robust- of time series data

[David Jacobs <jacobs.184@sociology.osu.edu>]

Although I agree with the prior response suggesting the Newey-West 
estimator, I wonder if this is necessary.  You are far more likely to 
encounter problems with serial correlation rather than heteroskedasticity 
when you estimate time-series models.  Did you test for 
heteroskedasticity?  I would only worry about heteroskedasticity if my 
time-series models flunk the relevant tests.

Dave Jacobs

At 09:24 AM 10/1/2003 -0700, you wrote:

> A perhaps naive question: Does it make sense to use the -robust-
> option (sandwitch variance estimate) in a ML estimation of a time
> series model? What is the variance estimates robust to in this case?
> Serial correlations? Thanks.
>
> Eddy
>
> __________________________________
> Do you Yahoo!?
> The New Yahoo! Shopping - with improved product search
> http://shopping.yahoo.com
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/