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: vce(robust) and suest based Hausman


From   Ioannis Tikoudis <ioannis.tikoudis@abe.kth.se>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: vce(robust) and suest based Hausman
Date   Mon, 11 Jul 2011 16:16:57 +0200

Dear Statalist,

I have the following questions on mlogit:

1) It seems that is possible to estimate an MNL model and get an adjusted covariance matrix for the MNL estimators. While this is straightforward in OLS (using the residual covariance matrix), I do not follow how this is done in STATA. So does it replace the standard MNL choice probabilities in the last iteration of the likelihood maximization, with other choice probabilities?

2) what is the exact difference between the McFadden Hausman IIA test and the suest based Hausman test? What is the test statistic of the last one and how is it performed? Thank you very much in advance

--
Ioannis Tikoudis
(M.Phil, Tek.Lic)
Division of Economics
The Royal Institute of Technology
Drottning Kristinas väg 30
SE-100 44 Stockholm

Phone: +46 (0) 87906969
Cell:  +46 (0) 739193271

*
*   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