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

st: Re: far5 and stcompet


From   "Elizabeth Breeze" <e.breeze@ucl.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: far5 and stcompet
Date   Mon, 15 Aug 2005 15:10:50 +0100 (GMT Daylight Time)

I have two queries.
First, is there a version of far5 (floating absolute risks) for Stata 8? I
tried the version I could download from the stata website and could not
use the command stcox as it still refers to cox. I tried without using the
cmd option and obtained different point estimates to those obtained from
stcox.

Second, it has been suggested to me that I try a competing risks model for
mortality from different diseases. I was modelling CVD mortality and
mortality from respiratory disease according to body mass index.  The
comment was that "this type of hazard modelling allows one to test if the
effects of the same predictors differ across the competing risks (of
different causes of death)". I had censored people at time of death,
regardless of cause, when using stcox and run separate models for the two
outcomes.  I found the command stcompet but am not clear what this does
nor how to try it out as I did not know what the variables  'time' 'stage'
'dead' referred to in the example given . I was surprised that the outcome
was not 'dead'.  Suggestions welcome. As you can probably tell, I am not
well versed in competing risks.

Thank you

Elizabeth Breeze, UCL


*
*   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