Dear Statalisters:
I know for ML estimation, lrtest offers Chow-type
tests of the
stability of whole set of coefficients in the
following way.
. logit depvar xlist
. est store All
. logit depvar xlist if regiem1
. est store A1
. logit depvar xlist if regiem2
. est store A2
...
. lrtest (All) (A1 A2 ..), df(#)
Here # should be the number of variables for the whole
coefficients,
isn't it?
But how to test if I concern only whether a subset of
coefficients
experience structural changes over time?
I feel this is just to test a specific part of A1 and
A2 (A3..) is
equal and should be quite simple, but don't know how
to do it in stata. Sorry for my limited stata
knowledge.
Thanks!
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
*
* 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/
