[R] Shared Frailty in survival package (left truncation, time-dep. covariates)

[Thomas Lumley]

On Tue, 31 May 2005, Stefan Pohl wrote:

> Dear list,
>
> I want o fit a shared gamma frailty model with the frailty specification 
> in the survival package.
>
> I have partly left-truncated data and time-dependent covariates. Is it 
> possible to combine these two things in the frailty function. Or are the 
> results wrong if I use data in the start-stop-formulation which account 
> for delayed entry?

It should work: as usual in the Cox model you get left-truncation and 
time-dependent covariates for free, since the partial likelihood only 
considers one risk set at a time.  You do need to make sure you specify 
the correct id variable, of course, and left truncation may reduce the 
amount of information available for estimating the frailty.


 	-thomas