Statalist


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

Re: st: Decomposing logistic regression


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Decomposing logistic regression
Date   Wed, 7 Oct 2009 11:39:43 +0000 (GMT)

--- On Wed, 7/10/09, Rajaram Subramanian Potty wrote:
> The estimated logistic equation can be used to predict the 
> probability conditional upon the relevant values of the
> determining variable. Using these predicted probabilities,
> one can compute, using the methodology of inequality
> decomposition, how much of the over all inequality in these
> probability can be explained by a particular factor.

The concept of explained variance is pretty much unique to
linear regression/OLS/ANOVA. Especially the decomposition
of these variances rely heavily on linearity of the effects. 
There are pseudo R^2 for non-linear models like -logit-, but 
because the effects have to be non-linear I doubt whether 
one can decompose those.

Hope this helps,
Maarten

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

http://www.maartenbuis.nl
--------------------------

Send instant messages to your online friends http://uk.messenger.yahoo.com 

*
*   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