zbMATH — the first resource for mathematics

Computational issues for quantile regression. (English) Zbl 1192.62114
Summary: 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, and 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.

62G08 Nonparametric regression and quantile regression
65C60 Computational problems in statistics (MSC2010)
90C05 Linear programming
62G15 Nonparametric tolerance and confidence regions