Home > Research > Publications & Outputs > Series estimation of functional-coefficient par...

Research

Associated organisational units

Electronic data

  • FCPLR-Series-Feb-2016

    Rights statement: This is an Accepted Manuscript of an article published by Taylor & Francis in Communications in Statistics - Theory and Methods on 21/07/2016, available online: http://www.tandfonline.com/10.1080/03610926.2016.1157189

    Accepted author manuscript, 739 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

Keywords

View graph of relations

Series estimation of functional-coefficient partially linear regression model

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published
<mark>Journal publication date</mark>10/08/2016
<mark>Journal</mark>Communications in Statistics - Theory and Methods
Issue number15
Volume46
Number of pages10
Pages (from-to)7593-7602
Publication StatusPublished
Early online date21/07/16
<mark>Original language</mark>English

Abstract

This paper develops an alternative and complement estimation procedure for functional coefficient partially linear regression (FCPLR) model based on series method. We derive the convergence rates and asymptotic normality of the proposed estimator. We examine its finite sample performance and compare it with the two-step local linear estimator via a small scale Monte Carlo simulation.

Bibliographic note

This is an Accepted Manuscript of an article published by Taylor & Francis in Communications in Statistics - Theory and Methods on 21/07/2016, available online: http://www.tandfonline.com/10.1080/03610926.2016.1157189