Selection consistency of EBIC for GLIM with non-canonical links and diverging number of parameters

DOI10.4310/SII.2013.V6.N2.A10MaRDI QIDQ897180zbMATH OpenFDO

Authors Zehua Chen, Shan Luo

Publication date 17 December 2015

Published in Statistics and Its Interface (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1112.2815

zbMATH Keywords

variable selectiongeneralized linear modelselection consistencyextended BICnon-canonical links

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10) Statistical ranking and selection procedures (62F07) Generalized linear models (logistic models) (62J12)

Abstract: In this article, we investigate the properties of the EBIC in variable selection for generalized linear models with non-canonical links and diverging number of parameters in ultra-high dimensional feature space. The selection consistency of the EBIC in this situation is established under moderate conditions. The finite sample performance of the EBIC coupled with a forward selection procedure is demonstrated through simulation studies and a real data analysis.

Recommendations

• Variable selection in generalized linear models with canonical link functions
• The consistency of variable selection for generalized linear models
• scientific article; zbMATH DE number 2063715
• Robust variable selection for generalized linear models with a diverging number of parameters
• Nonparametric estimation of the link function including variable selection
• A deviance-based criterion for model selection in GLM
• Consistency of Bayesian linear model selection with a growing number of parameters
• GLS discrepancy based information criteria for selecting covariance structure models
• Consistency of hyper-\(g\)-prior-based Bayesian variable selection for generalized linear models
• Robust variable selection for nonlinear models with diverging number of parameters

Cited in

(6)

• The consistency of variable selection for generalized linear models
• Polynomial network autoregressive models with divergent orders
• Extended BIC for small-\(n\)-large-\(P\) sparse GLM
• High-dimensional Ising model selection with Bayesian information criteria
• Extended Bayesian information criterion in the Cox model with a high-dimensional feature space
• Extended BIC for linear regression models with diverging number of relevant features and high or ultra-high feature spaces

This page was built for publication: Selection consistency of EBIC for GLIM with non-canonical links and diverging number of parameters

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q897180)