Blockwise AICc for model selection in generalized linear models

Song, Guofeng, Dong, Xiaogang, Wu, Jiafeng and Wang, You-Gan (2017) Blockwise AICc for model selection in generalized linear models. Environmental Modeling and Assessment, 1-11. doi:10.1007/s10666-017-9552-8


Author Song, Guofeng
Dong, Xiaogang
Wu, Jiafeng
Wang, You-Gan
Title Blockwise AICc for model selection in generalized linear models
Journal name Environmental Modeling and Assessment   Check publisher's open access policy
ISSN 1573-2967
1420-2026
Publication date 2017-03-09
Sub-type Article (original research)
DOI 10.1007/s10666-017-9552-8
Open Access Status Not yet assessed
Start page 1
End page 11
Total pages 11
Place of publication Dordrecht, Netherlands
Publisher Springer Netherlands
Collection year 2018
Language eng
Abstract The corrected Akaike information criterion (AICc) is a widely used tool in analyzing environmental and ecological data, and it outperforms the Akaike information criterion (AIC), especially in small-size samples. To take advantage of this property, we propose a modified version of the AICc in a generalized linear model framework, referred to as the blockwise AICc (bAICc). Compared with some other information criteria, extensive simulation results show that the bAICc performs well. We also analyzed two environmental datasets, one for snail survival and the other for fish infection, to illustrate the usefulness of this new model selection criterion.
Keyword AIC
AICc
Environmental applications
Model selection
Quasi-likelihood
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: School of Mathematics and Physics
HERDC Pre-Audit
 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 28 Mar 2017, 00:20:19 EST by Web Cron on behalf of Learning and Research Services (UQ Library)