Testing the specification of a fitted autoregressive-moving average model

D. S. Poskitt, A. R. Tremayne

Research output: Contribution to journalArticleResearchpeer-review

29 Citations (Scopus)

Abstract

SUMMARY: This paper provides an extension of the application of score, or Lagrangian multiplier, tests to diagnostic checking of ARMA, autoregressive-moving average, models. The score test procedure for testing the null hypothesis of an ARMA(p,q) process against certain ARMA (p{squared plus}r, q{squared plus}s) alternatives is considered and shown to be of the form of a pure significance test.

Original languageEnglish
Pages (from-to)359-363
Number of pages5
JournalBiometrika
Volume67
Issue number2
DOIs
Publication statusPublished - 1 Dec 1980
Externally publishedYes

Keywords

  • Autoregressive-moving average model
  • Significance test
  • Singular information matrix.

Cite this