Selection of the order of an autoregressive model by Akaike's information criterion

1976 Biometrika 778 citations

Abstract

The asymptotic distribution is obtained of the order of regression selected by Akaike's information criterion in autoregressive models. The asymptotic quadratic risks of estimates of regression parameters are evaluated when the order is selected by this method. Some results of computational experiments are given.

Keywords

Akaike information criterionMathematicsAutoregressive modelBayesian information criterionModel selectionStatisticsInformation CriteriaSelection (genetic algorithm)Applied mathematicsStepwise regressionSTAR modelEconometricsAutoregressive integrated moving averageTime seriesArtificial intelligence

Affiliated Institutions

Related Publications

Adaptive Model Selection

AbstractMost model selection procedures use a fixed penalty penalizing an increase in the size of a model. These nonadaptive selection procedures perform well only in one type o...

2002 Journal of the American Statistical A... 195 citations

Publication Info

Year
1976
Type
article
Volume
63
Issue
1
Pages
117-126
Citations
778
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

778
OpenAlex

Cite This

Ritei Shibata (1976). Selection of the order of an autoregressive model by Akaike's information criterion. Biometrika , 63 (1) , 117-126. https://doi.org/10.1093/biomet/63.1.117

Identifiers

DOI
10.1093/biomet/63.1.117