Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: do you HAVE to have endogenous time-invariant variable when running xthtaylor?


From   Mei Liu <mei.liu.yuki@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: do you HAVE to have endogenous time-invariant variable when running xthtaylor?
Date   Sun, 18 Apr 2010 13:19:34 -0400

Hi,

I have a question about Stata's Hausman Taylor Estimator for panel
data. The Stata command is xthtaylor.

Usually, under the xthtaylor framework, you will have to sepicify the
"endogenous" variables in your time-varying variables and the
"endogenous" variables among your time-invariant variables. The
variables can be "endogenous" in the sense that they can be correlated
with the random effects.

What if there is NO endogenous time-invariant variable in the model?
That is to say, all the time-invariant variables are exogenous.

The model I am currently working with have time-varying exogenous
variables, time-varying endogenous variables, and time-invariant
exogenous variables. I have no time-invariant variable in the variable
list for endog(varlist).  Xthtaylor will still run. However, I am not
sure if the estimated coefficients are still consistent?

Any suggestions will be deeply appreciated.

Best,
Mei
*
*   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   |   Site index