Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

st: Proportional hazard assumption


From   Grethe Søndergaard <dkstatstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Proportional hazard assumption
Date   Fri, 27 May 2011 08:24:02 +0200

Hi,

A while ago I asked you about your help regarding test of the
proportional hazard assumption when the stratas you include are very
small (2-6 individuals). I got some useful responses but I have got
two additional questions:

Question 1)
If the graph that this plot creates is horizontal will that indicate
that the proportional hazard assumption is met?
Stcox i.education, strata(stratum_variable) scaledsch(sca*) schoenfeld(sch*)
Stphtest, rank plot (i.education)

Question 2)
Age is the underlying time scale. I have tried to stsplit my data in
death (the outcome) before and after age 45 to test if there is a
better goodness of fit in the two age-specific models compared to the
full model. I would like to use "estimates store" and "lrtest" to do
this - but is this possible when I need to compare the full models
with the two age-specific models at the same time?

Thank you

Grethe
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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   |   Site index