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

st: risk-adjusted modeling


From   Lily Huang <lily6941@yahoo.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: risk-adjusted modeling
Date   Tue, 1 Jul 2003 13:46:02 -0700 (PDT)

I have a very large data set with more than 100
independent variables.  I am trying to do a
risk-adjusted model for hospitalization.  The
dependent variable was created based on a
hospitalization event during the first 7 days of a
home care admission and was coded as 0 and 1.  However
the rate of hospitalization of 7 days is very rare
(2.7%).  My questions is

(1)May I apply a Poisson regression model in this
situation?  If yes, how can I reduce independent
variables? If no, what is the best way that I should
try?

In addition, I also created variables that indicate if
a patient had a hospitalization event within 14, 21,
and 30 days.  I am going to try modeling how patientsí
characteristics at start of care relate to the
occurrence of an event within a certain time period.
Any suggestion of how I should approach this.   I am
new to statistics and am still learning.  Iíll really
appreciate your response.

Thanks.

Lily Padula


__________________________________
Do you Yahoo!?
SBC Yahoo! DSL - Now only $29.95 per month!
http://sbc.yahoo.com

*
*   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