I suspect you are using time series operators (l.varname)? Generate the
lagged variable before calling -xtreg- (see example below). You might want
to pass this on to Stata tech support
(http://www.stata.com/support/tech-support/)
Hope this helps,
Scott
. webuse grunfeld
. qui xtreg invest l.invest mvalue kstock, fe
. predict u_hat, u
not sorted
r(5);
. gen lag_invest = l.invest
(10 missing values generated)
. qui xtreg invest lag_invest mvalue kstock, fe
. predict u_hat, u
(10 missing values generated)
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Bob Rijkers
> Sent: Friday, August 19, 2005 4:28 AM
> To: [email protected]
> Cc: [email protected]
> Subject: st: Obtaining fixed effects using the predict command ; sorting
> issues
>
>
> To Whom It May Concern,
>
> I am estimating a fixed-effects model on a dynamic panel using the xtreg,
> fe command. I would like to obtain an estimate of the fixed effects. When
> I use the predict command (with option ,u for fixed effects) I get an
> error message telling me the data are not sorted. However, simply sorting
> the data by panel-variable and time-variable does not resolve the issue.
> My question is; what am I doing wrong? Or; how do I sort my data?
>
> Sincerely,
>
> Bob Rijkers
>
> PS Obviously, I could compute the fixed effects in a more roundabout
> fashion by calculating fitted values (the predict command does enable me
> to obtain fitted values), and computing the mean residual, but I have the
> gut feeling there must be an easier way of obtaining the fixed effects.
> *
> * 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/
