Focused information criterion and model averaging based on weighted composite quantile regression

Handle URI:
http://hdl.handle.net/10754/598348
Title:
Focused information criterion and model averaging based on weighted composite quantile regression
Authors:
Xu, Ganggang; Wang, Suojin; Huang, Jianhua Z.
Abstract:
We study the focused information criterion and frequentist model averaging and their application to post-model-selection inference for weighted composite quantile regression (WCQR) in the context of the additive partial linear models. With the non-parametric functions approximated by polynomial splines, we show that, under certain conditions, the asymptotic distribution of the frequentist model averaging WCQR-estimator of a focused parameter is a non-linear mixture of normal distributions. This asymptotic distribution is used to construct confidence intervals that achieve the nominal coverage probability. With properly chosen weights, the focused information criterion based WCQR estimators are not only robust to outliers and non-normal residuals but also can achieve efficiency close to the maximum likelihood estimator, without assuming the true error distribution. Simulation studies and a real data analysis are used to illustrate the effectiveness of the proposed procedure. © 2013 Board of the Foundation of the Scandinavian Journal of Statistics..
Citation:
Xu G, Wang S, Huang JZ (2013) Focused information criterion and model averaging based on weighted composite quantile regression. Scandinavian Journal of Statistics 41: 365–381. Available: http://dx.doi.org/10.1111/sjos.12034.
Publisher:
Wiley-Blackwell
Journal:
Scandinavian Journal of Statistics
KAUST Grant Number:
KUS-CI-016-04
Issue Date:
13-Aug-2013
DOI:
10.1111/sjos.12034
Type:
Article
ISSN:
0303-6898
Sponsors:
This research was partially supported by Award Number KUS-CI-016-04, made by King Abdullah University of Science and Technology (KAUST). Huang's research was also partially supported by NSF (DMS-0907170, DMS-1007618, DMS-1208952), NCI (CA57030). Part of this work was carried out while Wang was a visiting Professor at KAUST.
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorXu, Ganggangen
dc.contributor.authorWang, Suojinen
dc.contributor.authorHuang, Jianhua Z.en
dc.date.accessioned2016-02-25T13:19:09Zen
dc.date.available2016-02-25T13:19:09Zen
dc.date.issued2013-08-13en
dc.identifier.citationXu G, Wang S, Huang JZ (2013) Focused information criterion and model averaging based on weighted composite quantile regression. Scandinavian Journal of Statistics 41: 365–381. Available: http://dx.doi.org/10.1111/sjos.12034.en
dc.identifier.issn0303-6898en
dc.identifier.doi10.1111/sjos.12034en
dc.identifier.urihttp://hdl.handle.net/10754/598348en
dc.description.abstractWe study the focused information criterion and frequentist model averaging and their application to post-model-selection inference for weighted composite quantile regression (WCQR) in the context of the additive partial linear models. With the non-parametric functions approximated by polynomial splines, we show that, under certain conditions, the asymptotic distribution of the frequentist model averaging WCQR-estimator of a focused parameter is a non-linear mixture of normal distributions. This asymptotic distribution is used to construct confidence intervals that achieve the nominal coverage probability. With properly chosen weights, the focused information criterion based WCQR estimators are not only robust to outliers and non-normal residuals but also can achieve efficiency close to the maximum likelihood estimator, without assuming the true error distribution. Simulation studies and a real data analysis are used to illustrate the effectiveness of the proposed procedure. © 2013 Board of the Foundation of the Scandinavian Journal of Statistics..en
dc.description.sponsorshipThis research was partially supported by Award Number KUS-CI-016-04, made by King Abdullah University of Science and Technology (KAUST). Huang's research was also partially supported by NSF (DMS-0907170, DMS-1007618, DMS-1208952), NCI (CA57030). Part of this work was carried out while Wang was a visiting Professor at KAUST.en
dc.publisherWiley-Blackwellen
dc.subjectFocused information criterionen
dc.subjectFrequentist model averagingen
dc.subjectModel inferenceen
dc.subjectWeighted composite quantile estimatoren
dc.titleFocused information criterion and model averaging based on weighted composite quantile regressionen
dc.typeArticleen
dc.identifier.journalScandinavian Journal of Statisticsen
dc.contributor.institutionDepartment of Statistics; Texas A&M Universityen
kaust.grant.numberKUS-CI-016-04en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.