PRIMsrc (version 0.6.3)

predict.PRSP: Predict Function

Description

S3-generic predict function to predict the box membership and box vertices on an independent set.

Usage

# S3 method for PRSP
predict(object, 
                         newdata, 
                         steps, 
                         na.action = na.omit, ...)

Arguments

object

Object of class PRSP as generated by the main function sbh.

newdata

Either a numeric matrix or numeric vector containing the new input data of same dimensionality as the final PRSP object of used covariates. A vector will be transformed to a (\#sample x 1) matrix.

steps

Integer vector. Vector of peeling steps at which to predict the box memberships and box vertices. Defaults to the last peeling step only.

na.action

A function to specify the action to be taken if NAs are found. The default action is na.omit, which leads to rejection of incomplete cases.

…

Further generic arguments passed to the predict function.

Value

List containing the following 2 fields:

boxind

Logical matrix of predicted box membership indicator (columns) by peeling steps (rows). TRUE = in-box, FALSE = out-of-box.

vertices

List of size the number of chosen peeling steps where each entry is a numeric matrix of predicted box vertices: lower and upper bounds (rows) by covariate (columns).

References

• Dazard J-E., Choe M., LeBlanc M. and Rao J.S. (2015). "Cross-validation and Peeling Strategies for Survival Bump Hunting using Recursive Peeling Methods." Statistical Analysis and Data Mining (in press).
• Dazard J-E., Choe M., LeBlanc M. and Rao J.S. (2014). "Cross-Validation of Survival Bump Hunting by Recursive Peeling Methods." In JSM Proceedings, Survival Methods for Risk Estimation/Prediction Section. Boston, MA, USA. American Statistical Association IMS - JSM, p. 3366-3380.
• Dazard J-E., Choe M., LeBlanc M. and Rao J.S. (2015). "R package PRIMsrc: Bump Hunting by Patient Rule Induction Method for Survival, Regression and Classification." In JSM Proceedings, Statistical Programmers and Analysts Section. Seattle, WA, USA. American Statistical Association IMS - JSM, (in press).
• Dazard J-E. and J.S. Rao (2010). "Local Sparse Bump Hunting." J. Comp Graph. Statistics, 19(4):900-92.

Examples

#===================================================
# Loading the library and its dependencies
#===================================================
library("PRIMsrc")

#=================================================================================
# Simulated dataset #1 (n=250, p=3)
# Non Replicated Combined Cross-Validation (RCCV)
# Peeling criterion = LRT
# Optimization criterion = LRT
#=================================================================================
CVCOMB.synt1 <- sbh(dataset = Synthetic.1, 
                    cvtype = "combined", cvcriterion = "lrt",
                    B = 1, K = 5, 
                    vs = TRUE, cpv = FALSE, 
                    decimals = 2, probval = 0.5, 
                    arg = "beta=0.05,
                           alpha=0.1,
                           minn=10,
                           L=NULL,
                           peelcriterion=\"lr\"",
                    parallel = FALSE, conf = NULL, seed = 123)

n <- 100
p <- length(CVCOMB.synt1$cvfit$cv.used)
x <- matrix(data=runif(n=n*p, min=0, max=1),
            nrow=n, ncol=p, byrow=FALSE,
            dimnames=list(1:n, paste("X", 1:p, sep="")))
CVCOMB.pred <- predict(object=CVCOMB.synt1,
                       newdata=x,
                       steps=CVCOMB.synt1$cvfit$cv.nsteps)