I am interested in a panel data model with individual effects
decomposition. I want to estimate
y(it)=b*x(it) + g*z(i) + a(i) + e(it)
and get estimates of the coefficients g. XTHTAYLOR uses TSLS to estimate
this model, allowing for portions of x(it) and z(i) to be correlated with
the individual effect a(i).
Can I use XTHTAYLOR assuming no variables are correlated with a(i)? In
other words, is the endog(varlist_endog) option required? I don't yet have
Stata 8 so I can't just try this.
If not, does anyone have a reaction to this proposed method:
1. estimate y(it)=b*x(it) + a(i) + e(it)
2. regress ahat(i) on z(i) to estimate ghat, using bootstrap to get
standard errors right
Any citations or references would be appreciated.
Regards,
--Alex Cavallo
Lexecon
(312) 322-0208 voice
(312) 322-0218 fax
*
* 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/
