Skip to main content

New answers tagged

2 votes
Accepted

Survival analysis - any benefit to splitting on failure time instead of covariate change for creating time-varying covariates?

That sort of splitting helps if you want to define hazard ratios as explicit functions of time (ie, interactions between a covariate and a function of time). For example, if you want $\text{trt}\times ...
Thomas Lumley's user avatar

Top 50 recent answers are included