Statalist


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

Re: st: seqlogit consistency


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: seqlogit consistency
Date   Wed, 5 Aug 2009 01:39:56 +0000 (GMT)

--- On Tue, 4/8/09, KONSTANTARAS KONSTANTINOS wrote:
> having tried to estimate a sequential binary choice model
> by seqlogit and recognizing that only pseudo-likelihood
> estimates are reported, because it uses cluster correction
> for panel data,

Being the author of -seqlogit- I can tell you that this 
statement is incorrect: the default behavior of -seqlogit- 
is to use maximum likelihood without cluster correction.
You can do so if you want, but that decision is up to you.

There are potential issues with this model that have to do 
with unobserved heterogeneity. What I would suggest in that
case is to do a sensitivity analysis, to see whether these
potential issues are actually big enough problems to care 
about. I have done one such a study, where the results 
proved to be robust. This is just one study, so I will give
no guarantees that this is a general outcome. However,
-seqlogit- has tools to perform just such an analysis, so
you can easily do such a sensitivity analysis on your own 
model and convince yourself whether there is or is not a 
problem in your case. These tools are discussed here: 
http://home.fsw.vu.nl/m.buis/wp/unobserved_het.pdf .

Hope this helps,
Maarten

-----------------------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://home.fsw.vu.nl/m.buis/
-----------------------------------------


      

*
*   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   |   What's new   |   Site index