Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: logit


From   "Rajiv Mallick" <rmallick@hotmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: logit
Date   Tue, 01 Oct 2002 16:04:16 -0500

I am running a LOGIT where all my independent variables are dummies. I get the expected signs for them. But its ability to separate 1 from 0 is extremely poor. In fact my estimated probability scores turn out to be between 0 and .33. One another piece of information that may help is that the split between 1 and 0 (dependent variable) is 0.022/1.... I have very few 1s.

So the questions are:

1. Anything that one should be concerned when working with only quantitative variables?
2. Any other ways of handling data where the dependent variable split is just 0.022/1 That is I have in 5710 observations I have 127 bad (=1) and 5583 good (=0).

Rajiv






_________________________________________________________________
MSN Photos is the easiest way to share and print your photos: http://photos.msn.com/support/worldwide.aspx

*
* 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