Skip to main navigation Skip to search Skip to main content

Local polynomial modeling and bandwidth selection for time-varying linear models

  • The University of Hong Kong

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposes a local polynomial modeling approach and bandwidth selection algorithm for estimating time-varying linear models (TVLM). The time-varying coefficients of a TVLM are modeled locally by polynomials and estimated using least-squares estimation with a kernel having a certain bandwidth or support. Asymptotic behavior of the proposed estimator is established and it shows that there exists an optimal local bandwidth which minimizes the weighted mean squared error (MSE). A data-driven variable bandwidth selection method is also proposed to estimate this optimal bandwidth. Simulation results show that the proposed LPM method with adaptive bandwidth selection outperforms conventional TVLM identification methods in a large variety of testing conditions.

Original languageEnglish
Title of host publicationICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing
DOIs
StatePublished - 2009
Externally publishedYes
Event7th International Conference on Information, Communications and Signal Processing, ICICS 2009 - Macau Fisherman's Wharf, Macao
Duration: 8 Dec 200910 Dec 2009

Publication series

NameICICS 2009 - Conference Proceedings of the 7th International Conference on Information, Communications and Signal Processing

Conference

Conference7th International Conference on Information, Communications and Signal Processing, ICICS 2009
Country/TerritoryMacao
CityMacau Fisherman's Wharf
Period8/12/0910/12/09

Keywords

  • Bandwidth selection
  • Least-squares
  • Local polynomial modeling
  • Time-varying linear model

Fingerprint

Dive into the research topics of 'Local polynomial modeling and bandwidth selection for time-varying linear models'. Together they form a unique fingerprint.

Cite this