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

st: RE: -fracpoly-


From   COMBES Philippe <philippe.combes@ch-roanne.fr>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: -fracpoly-
Date   Fri, 13 Dec 2002 12:01:16 +0100

See Hosmer and Lemeshow : Applied Logistic Regression (2000) for good
explanations
Philippe

-----Original Message-----
From: david huffer [mailto:dhuffer@crim.umd.edu]
Sent: Friday, December 13, 2002 11:58 AM
To: Statalist
Subject: st: -fracpoly-


I have little experience using -fracpoly- and I am seeking advice.  

I have a variable AGE and a variable CAGE which is the centered version
of AGE and I want to find out whether in a binary logistic reg model I
should model age as linear or noinlinear in the logit.  When I estimate
a fractional polynomial regression using AGE, the findings indicate I
should treat age as linear in the logit.  When I use CAGE, the findings
indicate I should use a one-term polynomial transformation and model
CAGE as nonlinear.

Should I use the uncentered version in -fracpoly- or the centered
version?

Thanks in advance.


*
*   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