I have a survival analysis curve for two treatments over 5 years. It looks
like the curves diverge proportionally as time passes (i,e treatment effect
continues to be accrued /maintained over time?). Is it possible to perform
a statistical test on a 5 year survival curve for two treatments that will
establish if there is evidence of such a divergence of the two survival
curves? If so, can I come to the conclusion that, were the study to be
extended over ten years the survival curve would continue to diverge at the
same 'rate'.
Is this what the log rank test does ? Or is being able to establish
proportional hazards between the two treatments the answer? Is it possible
to answers from the curve alone (e.g. if a paper on the study only shows the
survival curves and you don't know the data behind it).
Thanks
_________________________________________________________________________
Get Your Private, Free E-mail from MSN Hotmail at http://www.hotmail.com.
Share information about yourself, create your own public profile at
http://profiles.msn.com.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|