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 at the end of May, and its replacement, statalist.org is already up and running.


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

st: Fwd: Heckman twostep: Goodness of fit and selection between nested models?


From   Lena Fredriksson <lena.fredriksson@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Fwd: Heckman twostep: Goodness of fit and selection between nested models?
Date   Tue, 15 Nov 2011 19:03:24 +0000

Dear Statalists,

I have a problem which is causing me great grief! I am estimating a
Heckman twostep model which I am quite happy with. However, departing
from this parsimonious model, I want carry out some kind of model
selection. However, my understanding is that *estat ic* (AIC, BIC
etc.) a) is inappropriate and b) does not work after Heckman twostep.
Consequently, my question is what information criteria to apply in
their absence? I have trawled the web without much luck.

Hoping for someone to enlighten me on this issue, pronto, as I am
running out of time...

Cheers,
Lena Fredriksson

*
*   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