Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: fixed effect, autocorrelation heteroskedasticity


From   David Jacobs <jacobs.184@sociology.osu.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: fixed effect, autocorrelation heteroskedasticity
Date   Sat, 23 Aug 2008 15:51:29 -0400

Economists often use -xtgls- and manually enter the dummies for cases (and years if you need 2-way fixed effects).

Another possibility is to use xtreg, fe and cluster on case id. This will correct the t-values for serial correlation, but you probably don't have enough cases in each cross-section. This approach might work if you enter less than about 10 explanatory variables, however.

By the way, the -xtreg, fe- routine in Stata 10 will warn you if you've exceeded the limits on the number of explanatory variables when you cluster on case id and the matrix is not full rank. But Stata 8.2 will not.

D. Jacobs



At 04:03 AM 8/23/2008, you wrote:

Hello everyone,

I'm working on a fixed effect model with n=14 and t=57. I found autocorrelation ( with xtserial and with xtregar ..., fe lbi) and heterosketasticity (with :xtreg ..., re//xttest0).
In order to correct autocorelation i use xtregar ..., fe
But xtregar could not use White correction for heteroskedasticity.

How I can do ? xtpcse or xtgls seem to be able to correct the two problems but do not keep fixed effect.

Ghislain.
I'm running Stata 8.2





*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index