Second-order bias-corrected AIC in multivariate normal linear models under non-normality

DOI10.1002/cjs.10090zbMath1349.62213MaRDI QIDQ3019147

Hirokazu Yanagihara, Ken-ichi Kamo, Tetsuji Tonda

Publication date: 27 July 2011

Published in: Canadian Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/cjs.10090

zbMATH Keywords

Kullback-Leibler information; bias correction; Akaike's information criterion; model misspecification; normal assumption; selection of variables; overspecified model; predicted residual sum of squares; robustness to non-normality; variance of information criterion

Mathematics Subject Classification ID

62H12: Estimation in multivariate analysis

62J05: Linear regression; mixed models

62F07: Statistical ranking and selection procedures

62B10: Statistical aspects of information-theoretic topics

Related Items

A class of cross-validatory model selection criteria, Jackknife bias correction of the AIC for selecting variables in canonical correlation analysis under model misspecification, A consistency property of the AIC for multivariate linear models when the dimension and the sample size are large, Iterative Bias Correction of the Cross-Validation Criterion

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A family of estimators for multivariate kurtosis in a nonnormal linear regression model
• Bootstrapping log likelihood and EIC, an extension of AIC
• Corrected versions of cross-validation criteria for selecting multivariate regression and growth curve models
• Corrected version of \(AIC\) for selecting multivariate normal linear regression models in a general nonnormal case
• Bias Corrections of some Criteria for Selecting Multivariate Linear Models in a General Nonnormal Case
• Regression and time series model selection in small samples
• Further analysis of the data by Akaike's information criterion and the finite corrections
• Information Criteria for Discriminating Among Alternative Regression Models
• A note on a power function of tukey' test for comparing three normal means with unequal sample sizes
• Modified AIC and Cp in multivariate linear regression
• Improvement to AIC as Estimator of Kullback–Leibler Information for Linear Model Selection
• IMPROVED ESTIMATION OF THE EXPECTED KULLBACK–LEIBLER DISCREPANCY IN CASE OF MISSPECIFICATION
• Model Selection for Multivariate Regression in Small Samples
• On a Class of Symmetric Nonnormal Distributions with a Kurtosis of Three
• Measures of multivariate skewness and kurtosis with applications
• Some Comments on C P
• On Information and Sufficiency