Generic function for extraction of predicted survival probabilities from a fitted survival model conforming to the interface required by pmpec
.
1  predictProb(object, response, x, ...)

object 
a fitted survival model. 
response 
Either a survival object (with 
x 

... 
additional arguments, for example model complexity or, in case of survival response, argument 
pmpec
requires a predictProb.class
function for each model fit of class class
. It extracts the predicted probability of survival from this model.
See existing predictProb
functions, at the time predictProb.CoxBoost
, predictProb.coxph
and predictProb.survfit
.
If desired predictProb
function for class class
is not available in peperr, but implemented in package pec as predictSurvProb.class
, it can easily be transformed as predictProb
method.
Matrix with predicted probabilities for each evaluation time point in times
(columns) and each new observation (rows).
Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.
Please suggest features or report bugs with the GitHub issue tracker.
All documentation is copyright its authors; we didn't write any of that.