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

RE: st: probit


From   "Scott Merryman" <smerryman@kc.rr.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: probit
Date   Thu, 17 Jun 2004 22:05:13 -0500

Following up on David's comment, there is a Stata FAQ on this topic at "How
does one estimate a model when the dependent variable is a proportion?"
(http://www.stata.com/support/faqs/stat/logit.html) and at the UCLA Academic
Technology Services: "How does one do regression when the dependent variable
is a proportion?" (http://www.ats.ucla.edu/stat/stata/faq/proportion.htm )

Hope this helps,

Scott


-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of David Greenberg
Sent: Thursday, June 17, 2004 6:25 PM
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: probit

You should not use probit (or logit). Treat your dependent variable as
continuous, ranging between 0 and 1. To linearize the equation, create a new
variable, ln[PIT/(1-PIT)] and treat that as a dependent variable. This will
work as long as you don't have values in which PIT is 0 or 1. If you do, you
may need to use a different transformation. 
- David Greenberg, Sociology Department, New York University


*
*   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