Statalist


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

st: MLOGIT versus a set of LOGIT models


From   "Jon Heron" <Jon.Heron@bristol.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   st: MLOGIT versus a set of LOGIT models
Date   Tue, 18 Aug 2009 17:14:21 +0100 (BST)

 Dear all,


 I have always believed that the regression estimates from a multinomial
logistic
 regression model (MLOGIT) could be replicated through a set of simple
 logit models with the appropriately derived binary outcomes.

 Whilst attempting to demonstrate this fact for some teaching material on
 polytomous IRT that i am writing, I moved from my usual categorical
 predictors to a continuous covariate + discovered that the above equivalence
 did not hold.

 To ensure that this was not a fluke, I have since demonstrated that with
 the two simple models below, each with the same 4-level outcome and 4-level
 predictor, the former can be replicated with logits, but not the latter.

 xi: mlogit ghq1 i.ghq3, baseoutcome(0)
 mlogit ghq1 ghq3, baseoutcome(0)


 please can anyone put me out of my misery?


 cheers,



 Jon
-- 
Dr Jon Heron
ALSPAC Stats Team Leader
Department of Social Medicine
University of Bristol
Oakfield House
Oakfield Grove
Bristol
BS8 2BN


*
*   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