An Efficient Algorithm for Calculating the Likelihood and Likelihood Gradient of ARMA Models

Research output: Contribution to journalArticlepeer-review

Abstract

We obtain exact analytical expressions for the likelihood and likelihood gradient of stationary autoregressive moving average (ARMA) models. Let us denote the sample size by N, the autoregressive order by p, and the moving average order by q. The calculation of the likelihood requires (p + 2q + 1)N + o(N) multiply-add operations, and the calculation of the likelihood gradient requires (2p + 6q + 2)N + o(N) multiply-add operations. These expressions may be used to obtain an iterative, Newton-Raphson-type converging algorithm, with superlinear convergence rate, that computes the maximum-likelihood estimator in (2p + 6q + 2)N + o(N) multiply-add operations per iteration.

Original languageEnglish
Pages (from-to)336-340
Number of pages5
JournalIEEE Transactions on Automatic Control
Volume38
Issue number2
DOIs
StatePublished - Feb 1993

Fingerprint

Dive into the research topics of 'An Efficient Algorithm for Calculating the Likelihood and Likelihood Gradient of ARMA Models'. Together they form a unique fingerprint.

Cite this