[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: stcox and basechazard
<firstname.lastname@example.org> points out an inconsistency in the estimation of the baseline
cumulative hazard using -stcox-.
> I would like to report what I believe is an erroneous result that is
> generated by Stata 7.
> After the estimation of a Cox proportional hazard model (stcox), I obtain a
> baseline cumulative hazard function that is NOT monotonically increasing
> with time. In particular, I obtain:
This is a bug, and it occurs only when one specifies the -efron- method for
handling ties. Also, as gc4 pointed out, the erroneous values occur at the
failure times for which there do exist ties.
We've added this bug to our things-to-do list.
* For searches and help try: