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

st: prediction


From   Kit Baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: prediction
Date   Fri, 5 Aug 2005 13:14:38 -0400

After the regression , I want to estimated death from the effect of
age and period, while setting the effects of gender to zero.

Compute the prediction using the sample mean of gender in the equation.
It would be easiest if you created e.g. male=(gender==1) and ran the regression
with male instead of i.gender. Then the effect of gender is the magnitude of the male coefficient. If the sample were equal #s M,F, the effect of age and period ignoring gender would be to set gender to its sample mean of 0.5. But if the sample mean of male is other than 0.5, set it to that and calculate the prediction appropriate for every individual having "average" gender. Calculate the linear prediction and then transform it into poisson's standard if that is what you want.

Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.html


*
* 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