Combining regression quantile estimators

Kejia Shan, Yuhong Yang

Research output: Contribution to journalArticle

9 Scopus citations

Abstract

Model selection for quantile regression is a challenging problem. In addition to the well-known general difficulty of model selection uncertainty, when quantiles at multiple probability levels are of interest, typically a single candidate does not serve all of them simultaneously. In this paper, we propose methods to combine quantile estimators. Oracle inequalities show that, at each given probability level, the combined estimators automatically perform nearly as well as the best candidate. Simulation and examples show that the proposed model combination approach often leads to a substantial gain in accuracy under global measures of performance.

Original languageEnglish (US)
Pages (from-to)1171-1191
Number of pages21
JournalStatistica Sinica
Volume19
Issue number3
StatePublished - Jul 2009

Keywords

  • Adaptive quantile regression
  • Aggregation of estimators
  • Model combination

Fingerprint Dive into the research topics of 'Combining regression quantile estimators'. Together they form a unique fingerprint.

Cite this