Quantile regression for dynamic partially linear varying coefficient time series models

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

10 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)49-66
Journal / PublicationJournal of Multivariate Analysis
Volume141
Publication statusPublished - 4 Jul 2015
Externally publishedYes

Abstract

In this article, we consider quantile regression method for partially linear varying coefficient models for semiparametric time series modeling. We propose estimation methods based on general series estimation. We establish convergence rates of the estimator and the root-n asymptotic normality of the finite-dimensional parameter in the linear part. We further propose penalization-based method for automatically specifying the linear part of the model as well as performing variable selection, and show the model selection consistency of this approach. We illustrate the performance of estimates using a simulation study.

Research Area(s)

  • Autoregressive models, Model structure recovery, SCAD penalty, Schwarz information criterion (SIC), Splines