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

st: RE: regression question


From   "Nichols, Austin" <ANichols@ui.urban.org>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: regression question
Date   Tue, 24 Aug 2004 12:59:36 -0400

Depends on the DGP, but you can try -tobit, ll(0) ul(1)- if you don't care
to write out your own estimator.
As it's hard to know what "almost uniform" means here, you might want to
think carefully about what the underlying distribution is that gives you the
truncation at 0 and 1.

-----Original Message-----
From: Thomas Mählmann [mailto:maehlmann@wiso.uni-koeln.de]
Sent: Tuesday, August 24, 2004 12:25 PM
To: statalist@hsphsun2.harvard.edu
Subject: st: regression question


Dear Statalist-Users,

I have the following regression question:

My dependent variable y is bounded between 0 and 1. Its empirical
distribution is almost uniform between these two values, but the frequency
of observing 0 or 1 is much higher then for a value in ]0,1[.

Now, using logistic regression implies dropping the observations with y
in ]0,1[, what I don't want to do.

What is the appropriate regression technique for such a dependent variable?

Any ideas?

Thanks for your support
Thomas

*
*   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/

*
*   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