Evaluate the misclassification rate, i.e. prediction error, for a fitted model on new data. To use as argument aggregation.fun
in peperr
call.
aggregation.misclass(full.data=NULL, response, x, model, cplx=NULL,
type=c("apparent", "noinf"), fullsample.attr = NULL, ...)
passed from peperr
, but not used for calculation of the misclassification rate.
vector of binary response.
n*p
matrix of covariates.
model fitted with fit.fun
.
passed from peperr
, but not necessary for calculation of the misclassification rate.
character.
passed from peperr
, but not necessary for calculation of the misclassification rate.
additional arguments, passed to predict
function.
Scalar, indicating the misclassification rate.
Misclassification rate is the ratio of observations for which prediction of response is wrong.