Hanke, Alex
2005-Jun-14 18:38 UTC
[R] Survfit,newdata and continuous time varying covariates
Hi All, I am working with three time varying covariates in a coxph model. I cannot seem to figure out how to use survfit and the newdata argument to provide estimated survival curves for two scenarios of one covariate while holding the other two at the mean value. Is it possible to display how estimated survival depends on alternative scenarios/profiles of a time varying covariate? Alex Hanke Department of Fisheries and Oceans St. Andrews Biological Station 531 Brandy Cove Road St. Andrews, NB Canada E5B 2L9 [[alternative HTML version deleted]]