predict.rq.pen.seq: Predictions from rq.pen.seq object

In rqPen: Penalized Quantile Regression

Predictions from rq.pen.seq object

Description

Predictions from rq.pen.seq object

Usage

## S3 method for class 'rq.pen.seq'
predict(
  object,
  newx,
  tau = NULL,
  a = NULL,
  lambda = NULL,
  modelsIndex = NULL,
  lambdaIndex = NULL,
  ...
)

Arguments

object	rq.pen.seq object
newx	Matrix of predictors
tau	Quantile of interest. Default is NULL, which will return all quantiles. Should not be specified if modelsIndex is used.
a	Tuning parameter of a. Default is NULL, which returns coefficients for all values of a. Should not be specified if modelsIndex is used.
lambda	Tuning parameter of \lambda. Default is NULL, which returns coefficients for all values of \lambda.
modelsIndex	Index of the models for which coefficients should be returned. Does not need to be specified if tau or a are specified.
lambdaIndex	Index of the lambda values for which coefficients should be returned. Does not need to be specified if lambda is specified.
...	Additional parameters passed to coef.rq.pen.seq()

Value

A matrix of predictions for each tau and a combination

Author(s)

Ben Sherwood, [e-mail]

Examples

x <- matrix(runif(800),ncol=8)
y <- 1 + x[,1] + x[,8] + (1+.5*x[,3])*rnorm(100)
m1 <- rq.pen(x,y,penalty="ENet",a=c(0,.5,1),tau=c(.25,.75),lambda=c(.1,.05,.01))
newx <- matrix(runif(80),ncol=8)
allCoefs <- predict(m1,newx)
targetCoefs <- predict(m1,newx,tau=.25,a=.5,lambda=.1)
idxApproach <- predict(m1,newx,modelsIndex=2)
bothIdxApproach <- predict(m1,newx,modelsIndex=2,lambdaIndex=1)

rqPen documentation built on Aug. 25, 2023, 1:07 a.m.