bootcov and cph error
Williams Scott wrote:
Hi all, I am trying to get bootstrap resampled estimates of covariates in a Cox model using cph (Design library). Using the following I get the error:
ddist2.abr <- datadist(data2.abr) options(datadist='ddist2.abr') cph1.abr <- cph(Surv(strt3.abr,loc3.abr)~cov.a.abr+cov.b.abr,
data=data2.abr, x=T, y=T)
boot.cph1 <- bootcov(cph1.abr, B=100, coef.reps=TRUE, pr=T)
1 Error in oosl(f, matxv(X, cof), Y) : not implemented for cph models Removing coef.reps argument works fine, but I really need the coefficients if at all possible. I cant find anything in the help files suggesting that I cant use coef.reps in a cph model. Any help appreciated. Cheers Scott
Sorry it's taken so long to get to this. The documentation needs to be clarified. Add loglik=FALSE to allow coef.reps=TRUE to work for cph models. Frank
_____________________________ Dr. Scott Williams MD Peter MacCallum Cancer Centre Melbourne, Australia scott.williams at petermac.org
Frank E Harrell Jr Professor and Chair School of Medicine
Department of Biostatistics Vanderbilt University