[Rd] Method=df for coxph in survival package

Terry Therneau therneau at mayo.edu
Wed Apr 18 15:02:47 CEST 2012

In that particular example the value of "4" was pulled out of the air.  
There is no particular justification.

There is a strong relationship between the "effective" degrees of 
freedom and the variance of the random effect, and I often find the df 
scale easier to interpret.  See the Hodges and Sargent paper in 
Biometrika (2001) for a nice explanation of the connection in linear models.

Terry T.

=======  begin included message =========

I've been following the example in the R help page:

coxph(Surv(time, status) ~ age + frailty(inst, df=4), lung)

Here, in this particular example they fixed the degrees of freedom for the
random institution effects to be 4.
But, how did they decide?

More information about the R-devel mailing list