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

st: AW: fit statistics for svy: mlogit

From   "Martin Weiss" <>
To   <>
Subject   st: AW: fit statistics for svy: mlogit
Date   Thu, 11 Feb 2010 16:21:17 +0100


You may want to consult [SVY], p. 76:

"Most standard commands are also fit using maximum likelihood. When used
with independently
distributed, nonweighted data, the likelihood to be maximized reflects the
joint probability distribution
of the data given the chosen model. With complex survey data, however, this
interpretation of the
likelihood is no longer valid, because survey data are weighted, not
independently distributed, or
both. Yet for survey data, (valid) parameter estimates for a given model can
be obtained using the
associated likelihood function with appropriate weighting. Because the
probabilistic interpretation no
longer holds, the likelihood here is instead called a pseudolikelihood, but
likelihood-ratio tests are no
longer valid."


-----Ursprüngliche Nachricht-----
[] Im Auftrag von Kate Perper
Gesendet: Donnerstag, 11. Februar 2010 15:54
Betreff: st: fit statistics for svy: mlogit


I'm wondering how I can get fit statistics when running an multinomial
logistic regression model while controlling for survey design.  svy: mlogit

When I run mlogit without svy, I can get log likelihood statistics, not so
when svy is included.



*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2020 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index