--- Michael McCulloch <[email protected]> wrote:
> How does one get the hazard for each group separately with stcox?
> I've become somewhat blithely accustomed to usint stcox to get the
> hazard ratio comparing groups. What I'd like to do is get the hazards
> separately for each group.
>
> For example,
> use http://www.stata-press.com/data/cgg/hip2, clear
> stcox protect, exactp
>
> will give me the hazard ratio of hip fractures given wearing of
> protective device. But what are the hazards of fracture separately in
> the groups wearing, and not wearing, the device?
In many types of survival analyses, including stcox, the hazard changes
over time. The unique selling point of -stcox- is that this change in
hazard over time is not modeled, so you can't make an error in
specifying how the hazard rate changes over time (you can make errors
on how the hazard rate changes over other variables though). This is
why Cox regression is sometimes called semi-parametric. This point is
explained on pages 21--24 of
http://home.fsw.vu.nl/m.buis/wp/survival.html . Even though the hazard
rates are not directly estimated by -stcox-, you can recover them after
you have estimated a Cox model. In Stata you can do this using
-stcurve-.
Hope this helps,
Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
__________________________________________________________
Sent from Yahoo! Mail.
A Smarter Email http://uk.docs.yahoo.com/nowyoucan.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/
