Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: xtreg and suest


From   "Daniel Hoechle" <daniel.hoechle@unibas.ch>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: xtreg and suest
Date   Fri, 7 Apr 2006 17:35:23 +0200

Dear all

I would like to estimate a fixed effects panel regression for two groups
of individuals (men and women, say). Then I would like to compare the
coefficients of the two models. However, the -suest- command seems not
to work in this instance because Stata is

      " unable to generate scores for model m1
        suest requires that predict allow the score option
        r(322);"

To give an example:

* snip
sysuse grunfeld, clear
gen GroupNr=cond(fn<7,1,2)
xtreg I F C if GroupNr==1, fe i(fn)
est store m1
xtreg I F C if GroupNr==2, fe i(fn)
est store m2
suest m1 m2
* This gives an error.
* snip

However, the whole procedure works if the fixed effects estimator is
estimated "by hand":

* snip
sysuse grunfeld, clear
gen GroupNr=cond(fn<7,1,2)
xi: reg I F C i.fn if GroupNr==1
est store m1
xi: reg I F C i.fn if GroupNr==2
est store m2
suest m1 m2
test [m1_mean]F = [m2_mean]F
* snip

The problem with my panel is that I have about 20'000 individuals.
Therefore, it is not possible for me to estimate the FE-models by aid of
dummy variables (Stata limit exceeded).

Is there a possibility to test for equality of parameter estimates in
the case of panels? How could I test for equality of the constant of two
fixed effects panel models?

Thanks a lot for looking into this matter.

Kind regards,
Daniel

 


*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index