Hello, I am performing cross-validation on a number of survival models fitted with the coxph function and would like to use the likelihood ratio test on the left-out cases as the criteria for comparison of PCA, SPCA, ridge, lasso, etc. Is there an easy way to do this? I think predict.coxph might be the answer but stumped on the implementation. For example, if I had fit <- coxph(Surv(time, status) ~ age + ph.ecog + strata(inst), lung[1:200,]) > fit Call: coxph(formula = Surv(time, status) ~ age + ph.ecog + strata(inst), data = lung[1:200, ]) coef exp(coef) se(coef) z p age 0.0125 1.01 0.0106 1.18 0.24000 ph.ecog 0.5371 1.71 0.1423 3.78 0.00016 Likelihood ratio test=19.7 on 2 df, p=5.17e-05 n= 198, number of events= 156 (2 observations deleted due to missingness) How to test likelihood of this model on lung[201:228,] ? Thanks for any advice, [[alternative HTML version deleted]]