Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: multiple dummy variables -ologit, gologit, mlogit


From   "Gonzalez, Carolina (CIAT)" <c.gonzalez@cgiar.org>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: multiple dummy variables -ologit, gologit, mlogit
Date   Thu, 13 Sep 2007 15:39:16 -0500

 Hi all,
 how do I interpret the coefficients of multiple dummy variables, if I have an ordered logit model, gologit and  mlogit model ?. For example if  I have a categorical independent variable with let's say 4 possible outcomes: A,B,C,D. If I recode this variable into 4 dummies and incorporate 3 (B,C, D) into a regression as 3 independent variables. My question now is, how does the result mean? Do I have to treat each dummy variable as an independent or I have to compare each dummy variable (B,C,D) with the dropped dummy variable (A)? 
thanks and regards Carolina




*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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