[R] Coxph with factors

[Kylie-Anne Richards]

Thank you again for your help.

Your suggestions worked perfect. The problems I had when using 
f.pom=factor(-3, levels=seq(-3,2.5, by=0.5)) were a silly mistake on my part 
(as suspected and dually pointed out).  Thanks for the notes on baseline. I 
was not aware of the inaccuracies when using it at z=0.

I will be back with questions on computationally efficient time dependant 
survival functions next month.

Cheers,
Kylie-Anne

----- Original Message ----- 
From: "Thomas Lumley" <tlumley at u.washington.edu>
To: "Kylie-Anne Richards" <kar at itga.com.au>
Cc: <r-help at stat.math.ethz.ch>
Sent: Sunday, July 17, 2005 1:19 AM
Subject: Re: [R] Coxph with factors


> On Sat, 16 Jul 2005, Thomas Lumley wrote:
>>
>> Yes, but you don't need to go via the baseline.  The survival curves for
>> any two covariate vectors z1 and z2 are related by
>>
>> S(t; z1)= S(t; z2)^(z1-z2)
>>
> Actually
>   S(t; z1)=S(t;z2) ^(beta'(z1-z2))
>
> of course.
>
>  -thomas
>