Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: epiconf for Cox regression model


From   "Zhiqiang Wang" <z.wang@uq.edu.au>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: epiconf for Cox regression model
Date   Fri, 13 Jun 2008 09:55:46 +1000

Hi May

-epiconf- is an old program. If you are using Stata 9 or 10, you may
want to use -chest- with different syntax 

Without looking at your data or the output, I cannot tell why you got
different results. However, there are several possible explanations. The
presence of missing values among confounding factors is one of them. 

Regards,
Zhiqiang 

Zhiqiang Wang, PhD
School of Medicine, University of Queensland
Room 317, Edith Cavell Building
Royal Brisbane & Women's Hospital
Herston QLD 4029
Australia
Tel: +61 7 3346 4811
Fax: +61 7 3346 4812
Email: z.wang@uq.edu.au

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of MAY BAYDOUN
Sent: Friday, 13 June 2008 2:56 AM
To: statalist@hsphsun2.harvard.edu
Subject: st: epiconf for Cox regression model

Dear Statalisters,

I was wondering if you could help me figure out how to
set up an epiconf command for Cox regression models.
Suppose the model is as follows:

stcox exposure smoke2 smoke3 sex ed_years

and I want to see which potential confounders included
in the model are changing the estimate the most, how
should I set up the epiconf command to match the
hazard ratios I am getting here in the full model. I
tried doing the following but it did not match the
hazard ratio of the exposure in the full model:

epiconf _t exposure smoke2 smoke3 sex ed_years if
_st==1,  con(ed_years) cat(sex smoke2
smoke3)model(cox) backward expos(exposure) dead(_d)
detail

I am getting HRs of 2.70 to 3.00 when I am supposed to
get an adjusted HR of 2.46 and the crude is 2.42. 

Thanks a lot for any help you can provide,

Best,

May

May Baydoun, PhD in Epidemiology (UNC-Chapel Hill)  Staff Scientist,
National Institute on Aging, NIH/IRP,  Biomedical Research Center,
Baltimore, MD


      
*
*   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