prismpredict: Partially Recursively Induced Structured Moderation

In yuhuilin619/prism: Partially Recursively Induced Structured Moderation

Description

Generate predicted values for new dataset from the result of prism or hprism object.

Usage

prismpredict(l, newdat, hvar = NULL)

Arguments

l	An rpart output for prism or hprism tree.
newdat	A data frame in which to look for variables with which to predict.
hvar	The hierarchical level variable for hprism tree, which is specified within double quotes. If unspecified, prism tree is fitted instead. See Example for detail.

Details

Models are built on the training set and then test observations were fed down each tree based on their x and w values, and a predicted value of the log survival time was estimated from the root nodes that each test observation fell into.

Examples

## Not run: 
prd1<-prismpredict(l.prism,newdat=Leuk)
prd2<-prismpredict(l.hprism,newdat=Leuk,hvar="tpi")
prd3<-prismpredict(l.hprism1,newdat=Leuk,hvar="tpi.m")

## End(Not run)

yuhuilin619/prism documentation built on July 18, 2019, 5:41 p.m.