logpl {survcomp} | R Documentation |
The function computes the log partial likelihood of a set of coefficients given some survival data.
logpl(pred, surv.time, surv.event, strata, na.rm = FALSE, verbose = FALSE)
surv.time |
vector of times to event occurrence |
surv.event |
vector of indicators for event occurrence |
pred |
linear predictors computed using the Cox model |
strata |
stratification variable |
na.rm |
|
verbose |
verbosity of the function |
vector of two elements: logpl
and event
for the estimation of the log partial likelihood and the number of events, respectively
Benjamin Haibe-Kains
Cox, D. R. (1972) "Regression Models and Life Tables", Journal of the Royal Statistical Society Series B, 34, pages 187–220.
set.seed(12345) age <- rnorm(100, 50, 10) stime <- rexp(100) cens <- runif(100,.5,2) sevent <- as.numeric(stime <= cens) stime <- pmin(stime, cens) dd <- data.frame("stime"=stime, "sevent"=sevent, "age"=age) ##Cox model coxm <- coxph(Surv(stime, sevent) ~ age, data=dd) ##log partial likelihood of the null model logpl(pred=rep(0, nrow(dd)), surv.time=stime, surv.event=sevent) ##log partial likelihood of the Cox model logpl(pred=predict(object=coxm, newdata=dd), surv.time=stime, surv.event=sevent) ##equivalent to coxm$loglik