I'm looking at building a nomogram for cancer prognosis based on 20 variables. This will be derived from a cox ph model. In the past I used poor methodology including dichotomization and stepwise selection. I am looking to improve the methodology substantially on an upcoming study.
I understand that using Lasso for variable selection is now built into the glmnet R package. This is what I will use initially to select variables for cox regression.
However for internal validation, I understand that bootstrapping may be a superior process to k-fold cross validation.
While I am reasonably familiar with R, this methodological sequence to build the nomogram is very foreign to me. In terms of work flow, can anyone point me in the right direction on how to build a Cox PH model with Lasso that is internally validated with bootstrapping?