Bob,
From: Bob Rijkers <[email protected]>
Date sent: Mon, 14 Mar 2005 11:08:39 +0000 (GMT)
To: [email protected]
Subject: st: Question about Fixed Effects with lagged Explanatory Variables
Send reply to: [email protected]
>
> Hi,
>
> This is a follow-up on my previous e-mail which was perhaps not clear
> enough. My problem is not that I include a lagged value of the
> dependent variable as regressor in fixed estimation, but rather that I
> use a lag of an explanatory variable as an additional regressor. That
> is, I regress industrial productivity on proportion of the workforce
> trained this year, as well as on the proportion of the workforce the
> year before using the command xtreg, fe.
>
> Stata does not allow me to do this directly; the error message is that
> time-series operators are not allowed. When I generate a new variable
> for proportion of the workforce trained a year before, and thus do not
> use the lag-specification, my estimation goes through.
>
> My question is: am I doing something 'illegal' by recoding my variable
> and making the estimation go through; are there inherent econometric
> problems with using the lag of an explanatory variable as an
> additional regressor?
No and no. For whatever reason, xtreg doesn't allow time-series
operators (even though, for example, xtivreg does). What you are
doing is fine.
--MS
>
> Yours,
>
> Bob Rijkers
> *
> * 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/
Prof. Mark E. Schaffer
Director
Centre for Economic Reform and Transformation
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS UK
44-131-451-3494 direct
44-131-451-3296 fax
44-131-451-3485 CERT administrator
http://www.sml.hw.ac.uk/cert
*
* 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/
