Cited by 6,586Statistical Methods and InferenceStatistical Methods and ApplicationsStatistical and numerical algorithms

Regression and time series model selection in small samples

HURVICH, CLIFFORD M., TSAI, CHIH-LING·1989·Biometrika

Abstract

A bias correction to the Akaike information criterion, AIC, is derived for regression and autoregressive time series models. The correction is of particular use when the sample size is small, or when the number of fitted parameters is a moderate to large fraction of the sample size. The corrected method, called AICC, is asymptotically efficient if the true model is infinite dimensional. Furthermore, when the true model is of finite dimension, AICC is found to provide better model order choices than any other asymptotically efficient method. Applications to nonstationary autoregressive and mixed autoregressive moving average time series models are also discussed.

Integrity signals

Registry

Crossref · 10.1093/biomet/76.2.297

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The authors used an all-subsets model selection approach with AICc as selection criteria to account for limited sample size.

    “We used an all‐subsets model selection approach (due to the small model set), with Akaike's Corrected Information Criterion (AICc) as our selection criteria to account for our limited sample size (Hurvich and Tsai 1989).”

    From River Otter Predation of Nesting Seabirds Along the Coasts of North America (2025) · cites this paper as Hurvich and Tsai 1989

Cites

Cited by

Sorted by citations

Authors
HURVICH, C. M., & TSAI, C.-L.
Affiliations
  • New York University (US)
  • University of California, Davis (US)
Venue
Biometrika
Published
1989
Volume
76
Issue
2
Pages
297-307
ISSN
  • 0006-3444 (ISSN-L)
  • 1464-3510
OpenAlex
W1968371014
Cited by
6,586
References
1
Citations by year
2026: 320 · 2025: 295 · 2024: 290 · 2023: 290 · 2022: 321 · 2021: 428 · 2020: 421 · 2019: 404 · 2018: 365 · 2017: 351 · 2016: 322 · 2015: 341 · 2014: 324 · 2013: 312 · 2012: 225
FWCI
7.25
Type
journal article
Language
en
Open access
closed
Locations
Biometrika (publishedVersion)
Funders
Innovative Research Group Project of the National Natural Science Foundation of China
Topics
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Inference
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
  • Physical Sciences › Mathematics › Applied Mathematics › Statistical and numerical algorithms
Keywords
Akaike information criterion, AICc, bias correction, model selection, small sample size, regression models, autoregressive time series, model order selection, non-stationary time series, asymptotic efficiency

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review