cqrReg: An R Package for Quantile and Composite Quantile Regression and Variable Selection

09/13/2017
by   Matthew Pietrosanu, et al.
0

The cqrReg package for R is the first to introduce a family of robust, high-dimensional regression models for quantile and composite quantile regression, both with and without an adaptive lasso penalty for variable selection. In this paper, we reformulate these quantile regression problems and present the estimators we implement in cqrReg using alternating direction method of multipliers (ADMM), majorize-minimization (MM), and coordinate descent (CD) algorithms. Our new approaches address the lack of publicly-available methods for (composite) quantile regression, both with and without regularization. We demonstrate the need for a variety of algorithms in later simulation studies. For comparison, we also introduce the widely-used interior point (IP) formulation and test our methods against the advanced IP algorithms in the existing quantreg package. Our simulation studies show that each of our methods, particularly MM and CD, excel in different settings such as with large or high-dimensional data sets, respectively, and outperform the methods currently implemented in quantreg. ADMM offers particular promise for future developments in its amenability to parallelization.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/31/2021

Asgl: A Python Package for Penalized Linear and Quantile Regression

Asg is a Python package that solves penalized linear regression and quan...
research
11/05/2021

Quantile index regression

Estimating the structures at high or low quantiles has become an importa...
research
09/10/2020

Directional quantile classifiers

We introduce classifiers based on directional quantiles. We derive theor...
research
04/17/2021

Mixed Effect Modeling and Variable Selection for Quantile Regression

It is known that the estimating equations for quantile regression (QR) c...
research
08/10/2023

Quantile regression outcome-adaptive lasso: variable selection for causal quantile treatment effect estimation

Quantile treatment effects (QTEs) can characterize the potentially heter...
research
06/27/2020

The flare Package for High Dimensional Linear Regression and Precision Matrix Estimation in R

This paper describes an R package named flare, which implements a family...
research
06/12/2020

Detangling robustness in high dimensions: composite versus model-averaged estimation

Robust methods, though ubiquitous in practice, are yet to be fully under...

Please sign up or login with your details

Forgot password? Click here to reset