The professor of statistics at my PhD program said that omitting the constant radically changes your model. You should never omit it because if an intercept "really" exists, it is not wise to ask Stata to put it = 0; if the intercept is "really" zero, Stata will find it.
If none of the commands which I know implementing fixed effects and correcting for autocorrelation (unless you use the cluster(id) option) including -xtivreg-, -xtivreg2-, -gthacker-, -xtscc- allow you to drop the constanst, this should rise further concerns.
Nicola
At 02.33 05/10/2007 -0400, "Dohan Kim" wrote:
>Dear STATA group,
>
>I'm running cross-sectional time-series with AR(1) serial correlation
>using xtregar, fe. I want to run the model without constant, but STATA
>doesn't have noconstant option after xtregar.
>Is there any way I can suppress constant manually?
>
>Thanks in advance.
>
>- --
>Do Han Kim
>PhD Candidate,
>Dept. of Public Administration and Policy
>Rockefeller College, University at Albany
*
* 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/
