Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

RE: st: Sig Diff MFX probabilities

From   Ron Varga <[email protected]>
To   <[email protected]>
Subject   RE: st: Sig Diff MFX probabilities
Date   Fri, 16 Mar 2012 02:21:51 +1100

Still unclear. Using Stata10 I'm analysing 61 binary variables across 7 categories. Holding all variables from 5 categories at mean - understand ill-logical - and 1 binary variable from 1 category set to 1 - occurring and exhaustively all others from the same category not occurring - and another variable from the last category set to 1 and then 0, I generate MFX probabilities. How do I test if mfx using means for 5 categories and occuring for 2 defined attibutes significantly varies?  


*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index