A novel AIC variant for linear regression models based on a bootstrap correction

Abd Krim Seghouane

doi:10.1109/MLSP.2008.4685469

A novel AIC variant for linear regression models based on a bootstrap correction

Abd Krim Seghouane^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

The Akaike information criterion, AIC, and its corrected version, AIC _c are two methods for selecting normal linear regression models. Both criteria were designed as estimators of the expected Kullback-Leibler information between the model generating the data and the approximating candidate model. In this paper, a new corrected variants of AIC is derived for the purpose of small sample linear regression model selection. The new proposed variant of AIC is based on asymptotic approximation of bootstrap type estimates of Kullback-Leibler information. Simulation results which illustrate better performance of the proposed AIC correction when applied to polynomial regression in comparison to AlC, AIC_c and other criteria are presented. Asymptotic justifications for the proposed criterion are provided in the Appendix.

Original language	English
Title of host publication	Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008
Pages	139-144
Number of pages	6
DOIs	https://doi.org/10.1109/MLSP.2008.4685469
Publication status	Published - 2008
Event	2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008 - Cancun, Mexico Duration: 16 Oct 2008 → 19 Oct 2008

Publication series

Name	Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008

Conference

Conference	2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008
Country/Territory	Mexico
City	Cancun
Period	16/10/08 → 19/10/08

Access to Document

10.1109/MLSP.2008.4685469

Cite this

@inproceedings{dc5400af3a61449ba4d8905bbf306794,

title = "A novel AIC variant for linear regression models based on a bootstrap correction",

abstract = "The Akaike information criterion, AIC, and its corrected version, AIC c are two methods for selecting normal linear regression models. Both criteria were designed as estimators of the expected Kullback-Leibler information between the model generating the data and the approximating candidate model. In this paper, a new corrected variants of AIC is derived for the purpose of small sample linear regression model selection. The new proposed variant of AIC is based on asymptotic approximation of bootstrap type estimates of Kullback-Leibler information. Simulation results which illustrate better performance of the proposed AIC correction when applied to polynomial regression in comparison to AlC, AICc and other criteria are presented. Asymptotic justifications for the proposed criterion are provided in the Appendix.",

author = "Seghouane, {Abd Krim}",

year = "2008",

doi = "10.1109/MLSP.2008.4685469",

language = "English",

isbn = "9781424423767",

series = "Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008",

pages = "139--144",

booktitle = "Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008",

note = "2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008 ; Conference date: 16-10-2008 Through 19-10-2008",

}

Seghouane, AK 2008, A novel AIC variant for linear regression models based on a bootstrap correction. in Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008., 4685469, Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008, pp. 139-144, 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008, Cancun, Mexico, 16/10/08. https://doi.org/10.1109/MLSP.2008.4685469

A novel AIC variant for linear regression models based on a bootstrap correction. / Seghouane, Abd Krim.
Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008. 2008. p. 139-144 4685469 (Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A novel AIC variant for linear regression models based on a bootstrap correction

AU - Seghouane, Abd Krim

PY - 2008

Y1 - 2008

N2 - The Akaike information criterion, AIC, and its corrected version, AIC c are two methods for selecting normal linear regression models. Both criteria were designed as estimators of the expected Kullback-Leibler information between the model generating the data and the approximating candidate model. In this paper, a new corrected variants of AIC is derived for the purpose of small sample linear regression model selection. The new proposed variant of AIC is based on asymptotic approximation of bootstrap type estimates of Kullback-Leibler information. Simulation results which illustrate better performance of the proposed AIC correction when applied to polynomial regression in comparison to AlC, AICc and other criteria are presented. Asymptotic justifications for the proposed criterion are provided in the Appendix.

AB - The Akaike information criterion, AIC, and its corrected version, AIC c are two methods for selecting normal linear regression models. Both criteria were designed as estimators of the expected Kullback-Leibler information between the model generating the data and the approximating candidate model. In this paper, a new corrected variants of AIC is derived for the purpose of small sample linear regression model selection. The new proposed variant of AIC is based on asymptotic approximation of bootstrap type estimates of Kullback-Leibler information. Simulation results which illustrate better performance of the proposed AIC correction when applied to polynomial regression in comparison to AlC, AICc and other criteria are presented. Asymptotic justifications for the proposed criterion are provided in the Appendix.

UR - http://www.scopus.com/inward/record.url?scp=58049139196&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2008.4685469

DO - 10.1109/MLSP.2008.4685469

M3 - Conference contribution

SN - 9781424423767

T3 - Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008

SP - 139

EP - 144

BT - Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008

T2 - 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008

Y2 - 16 October 2008 through 19 October 2008

ER -

A novel AIC variant for linear regression models based on a bootstrap correction

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this