Sankhya: The Indian Journal of Statistics

2005, Volume 67, Pt. 2, 399--417

Computational Issues for Quantile Regression

By

Colin Chen, SAS Institute Inc. Cary, NC, USA
Ying Wei, Columbia University, NY, USA

SUMMARY. In this paper, we discuss some practical computational issues for quantile regression.  We consider the computation from two aspects: estimation and inference. For estimation, we cover three algorithms: simplex, interior point, and smoothing. We describe and compare these algorithms, then discuss implementation of some computing techniques, which include optimization, parallelization, and sparse computation, with these algorithms in practice. For inference, we focus on confidence intervals. We discuss three methods: sparsity, rank-score, and resampling. Their performances are compared for data sets with a large number of covariates.

AMS (1991) subject classification. Primary 62F35; Secondary 62J99.

Key words and phrases. Quantile regression, host optimization, multithreading, sparse computing, smoothing algorithm, simplex, interior point, median regression, linear programming, preprocessing.

Full paper (PDF)