Conditional Akaike information under covariate shift with application to small area estimation

被引:2
|
作者
Kawakubo, Yuki [1 ]
Sugasawa, Shonosuke [2 ]
Kubokawa, Tatsuya [3 ]
机构
[1] Chiba Univ, Grad Sch Social Sci, Chiba, Japan
[2] Inst Stat Math, Risk Anal Res Ctr, Tokyo, Japan
[3] Univ Tokyo, Fac Econ, Tokyo, Japan
基金
日本学术振兴会;
关键词
Akaike information criterion; conditional AIC; covariate shift; linear mixed model; small area estimation; LINEAR MIXED MODELS; SELECTION; REGRESSION; CRITERIA; ERROR;
D O I
10.1002/cjs.11354
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
In this study, we consider the problem of selecting explanatory variables of fixed effects in linear mixed models under covariate shift, which is when the values of covariates in the model for prediction differ from those in the model for observed data. We construct a variable selection criterion based on the conditional Akaike information introduced by Vaida & Blanchard (2005). We focus especially on covariate shift in small area estimation and demonstrate the usefulness of the proposed criterion. In addition, numerical performance is investigated through simulations, one of which is a design-based simulation using a real dataset of land prices. The Canadian Journal of Statistics 46: 316-335; 2018 (c) 2018 Statistical Society of Canada
引用
收藏
页码:316 / 335
页数:20
相关论文
共 50 条