Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Re: Survival Analysis estat phtest with very large sample size--need help


From   graupel75@gmail.com
To   Statalist <statalist@hsphsun2.harvard.edu>
Subject   st: Re: Survival Analysis estat phtest with very large sample size--need help
Date   Mon, 9 Dec 2013 20:08:58 +0800

Hi Peter,

I suspect you find something useful in 'Applied Survival Analysis'
(Hosmer, Lemeshow and May, 2008); I just quickly looked through and
didn't see a specific ref, but it's pretty comprehensive.

You could also run a Possion after -stsplit- and see how different the
IRRs are from your HRs; this has a more restrictive constant hazard
assumption but if you have a large number of failure times it should
be OK.

http://biostat.mc.vanderbilt.edu/wiki/pub/Main/LisaKaltenbach/poissonregtalk.pdf

Another option is to use flex parametric models (from ssc -stpm2-)
which allow much more freedom to model tvcs; if the hazard ratios are
basically unchanged, then you can feel confident using Cox even with
PH violations.

cheers-
Andrew Lover

______________________________________________
Epidemiologist
Centre for Infectious Disease Epidemiology Research (CIDER)
Saw Swee Hock School of Public Health
National University of Singapore
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index