[R] Apparently Conflicting Results with coxph

[Terry Therneau]

> I thought about this some more, and I'm not sure that possibility is
> "to blame."  In my time-dependent model, I don't think I'm doing
> anything different than is done for transplant in the Stanford
> Heart Study (the often used example for this kind of time-dependent
> covariate).  As in my case, you would not transplant a dead patient.
> So, I remain puzzled as to why my model is misbehaving.

  The Stanford Heart Study, quoted in nearly every survival book as you say, is 
a bit of an anomaly.  At the time it was run a good tissue match between the 
donor heart and the recipient was considered very important.  When a donor 
became available, the best match (or near best) among those waiting was chosen 
to recieve it.  Since the donor genetics are unpredictable, this is essentially 
equal to a random pick from those waiting.  The Stanford study is nearly alone 
in examples of time-dependent treatment in not having selection effects.
  
  	Terry T.