Learn R Programming

rqPen: Penalized quantile regression

Overview

This R package provides tools for estimating a quantile regression model with a penalized objective function. Implements a variety of penalties, including group penalties.

Installation

For most up to date versions use the following code. However, be warned the github package is often in a state of testing and debugging.

devtools::install_github("bssherwood/rqpen")

The following code will install the more stable CRAN version.

install.packages("rqPen")

Example

library(rqPen)
n<- 200
p<- 30
x0<- matrix(rnorm(n*p),n,p)
x<- cbind(x0, x0^2, x0^3)[,order(rep(1:p,3))]
y<- -2+x[,1]+0.5*x[,2]-x[,3]-0.5*x[,7]+x[,8]-0.2*x[,9]+rt(n,2)
group<- rep(1:p, each=3)

# lasso estimation
# one tau
fit1 <- rq.pen(x,y)
# several values of tau
fit2 <- rq.pen(x,y,tau=c(.2,.5,.8))

# Group SCAD estimation
fit3 <- rq.group.pen(x,y,groups=group,penalty="gSCAD")

# cross validation
cv1 <- rq.pen.cv(x,y)
plot(cv1)

cv2 <- rq.pen.cv(x,y,tau=c(.2,.5,.8))
plot(cv2)

cv3 <- rq.group.pen(x,y,groups=group,penalty="gSCAD")
plot(cv3)

# BIC selection of tuning parameters
qs1 <- qic.select(fit1)
qs2 <- qic.select(fit2)
qs3 <- qic.select(fit3)

See, https://github.com/bssherwood/rqpen/blob/master/ignore/rqPenArticle.pdf, for a vignette. The Huber approach for rq.pen relies on the R package hqreg and work presented in "Semismooth Newton Coordinate Descent Algorithm for Elastic-Net Penalized Huber Loss Regression and Quantile Regression". The Huber approach in rq.group.pen relies on R package hrqglas and work presented in An Efficient Approach to Feature Selection and Estimation for Quantile Regression with Grouped Variables

References

Sherwood, B. and Li, S. (2022) An Efficient Approach to Feature Selection and Estimation for Quantile Regression with Grouped Variables, Statistics and computing, 75.

Yi, C. and Huang, J. (2015) Semismooth Newton Coordinate Descent Algorithm for Elastic-Net Penalized Huber Loss Regression and Quantile Regression, Journal of Computational and Graphical Statistics, 26:3, 547-557.

Copy Link

Version

Install

install.packages('rqPen')

Monthly Downloads

806

Version

4.1.3

License

MIT + file LICENSE

Issues

0

Pull Requests

0

Stars

15

Forks

3

Maintainer

Ben Sherwood

Last Published

February 13th, 2025

Functions in rqPen (4.1.3)

plot.rq.pen.seq.cv

Plots cross validation results from a rq.pen.seq.cv object
print.qic.select

Print a qic.select object
print.rq.pen.seq

Print a rq.pen.seq object
plot.cv.rq.group.pen

Cross validation plot for cv.rq.group.pen object
plot.rq.pen.seq

Plot of coefficients of rq.pen.seq object as a function of lambda
rq.group.pen.cv

Performs cross validation for a group penalty.
rq.group.pen

Fits quantile regression models using a group penalized objective function.
rq.gq.pen.cv

Title Cross validation for consistent variable selection across multiple quantiles.
rq.group.fit

Estimates a quantile regression model with a group penalized objective function.
predict.cv.rq.pen

Prediction for a cv.rq.pen object
print.rq.pen.seq.cv

Prints a rq.pen.seq.cv object
qic

Calculate information criterion for penalized quantile regression models. Currently not exported.
qic.select

Select tuning parameters using IC
qic.select.rq.pen.seq

Select tuning parameters using IC
qic.select.rq.pen.seq.cv

Select tuning parameters using IC
rq.gq.pen

Title Quantile regression estimation and consistent variable selection across multiple quantiles
rq.pen.cv

Does k-folds cross validation for rq.pen. If multiple values of a are specified then does a grid based search for best value of \(\lambda\) and a.
rqPen

rqPen: A package for estimating quantile regression models using penalized objective functions.
rq.pen

Fit a quantile regression model using a penalized quantile loss function.
rq.lasso.fit

Estimates a quantile regression model with a lasso penalized quanitle loss function.
rq.nc.fit

Non-convex penalized quantile regression
cv.rq.group.pen

Old cross validation function for group penalty
coef.rq.pen.seq

Returns coefficients of a rq.pen.seq object
bytau.plot

Plot of how coefficients change with tau
coef.rq.pen.seq.cv

Returns coefficients from a rq.pen.seq.cv object.
bytau.plot.rq.pen.seq

Plot of how coefficients change with tau.
bytau.plot.rq.pen.seq.cv

Plot of coefficients varying by quantiles for rq.pen.seq.cv object
predict.rq.pen.seq

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

Predictions from rq.pen.seq.cv object
predict.qic.select

Predictions from a qic.select object
cv_plots

Plots of cross validation results as a function of lambda.
coef.cv.rq.group.pen

Coefficients from a cv.rq.group.pen object
coef.cv.rq.pen

Returns Coefficients of a cv.rq.pen object
predict.rq.pen

Prediction for a rq.pen object
beta_plots

Plots of coefficients by lambda for cv.rq.group.pen and cv.rq.pen