Selecting models with different spectral density matrix structures by the cross-validated log likelihood criterion

Yasumasa Matsuda, Yoshihiro Yajima, Howell Tong

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)

Abstract

We propose the cross-validated log likelihood (CVLL) criterion for selecting multivariate time series models with different forms of the spectral density matrix, which correspond to different constraints on the component time series such as mutual independence, separable correlation, time reversibility, graphical interaction and others. We obtain asymptotic properties of the CVLL, and demonstrate the empirical properties of the CVLL selection with both simulated and real data.

Original languageEnglish
Pages (from-to)221-249
Number of pages29
JournalBernoulli
Volume12
Issue number2
DOIs
Publication statusPublished - 2006 Apr

Keywords

  • Conditional independence
  • Consistency
  • Graphical model
  • Kullback-leibler divergence
  • Model selection
  • Multivariate time series
  • Periodogram
  • Spectral density matrix

ASJC Scopus subject areas

  • Statistics and Probability

Fingerprint Dive into the research topics of 'Selecting models with different spectral density matrix structures by the cross-validated log likelihood criterion'. Together they form a unique fingerprint.

Cite this