Statalist The Stata Listserver


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

Re: st: identification diagnostics for ml estimation?


From   "Stas Kolenikov" <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: identification diagnostics for ml estimation?
Date   Tue, 1 Aug 2006 09:18:46 -0500

No. The only diagnostics you could have from -ml- itself is that the
likelihood is not concave at the last iteration. -ml- is way too
general to look into those issues; they are up to the researcher to
determine, and code properly. Besides, there are models that are
underidentified only for certain parameter combinations (and
empirically underidentified near them), such as y=b_0 + b_1 x^b_2
which is underID when b_1==0 (value of b_2 cannot be determined) or
b_2 == 0 (only b_0+b_1 is identified).

On 7/31/06, Lian Jian <ljian@umich.edu> wrote:
Hi folks,

I am wondering if STATA offers any diagnostics of identification for
maximum likelihood estimations (with system of equations)? I have
looked both the statalist archives and Gould, Pitblado, and Sribney's
book, maximum likelihood estimation with stata (third ed).  I 'd
highly appreciate any suggestions/help.

thanks,
Lian
*
*   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/


--
Stas Kolenikov
http://stas.kolenikov.name
*
*   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