点击次数：

论文类型：期刊论文

发表时间：2014-02-01

发表刊物：JOURNAL OF APPLIED STATISTICS

收录刊物：SCIE、Scopus

卷号：41

期号：2

页面范围：393-406

ISSN号：0266-4763

关键字：multivariate generalized linear model; canonical link function; diverging number of parameters; model selection; consistency; Primary; 62J07; Secondary; 62J12

摘要：Generalized linear models (GLMs) are widely studied to deal with complex response variables. For the analysis of categorical dependent variables with more than two response categories, multivariate GLMs are presented to build the relationship between this polytomous response and a set of regressors. Traditional variable selection approaches have been proposed for the multivariate GLM with a canonical link function when the number of parameters is fixed in the literature. However, in many model selection problems, the number of parameters may be large and grow with the sample size. In this paper, we present a new selection criterion to the model with a diverging number of parameters. Under suitable conditions, the criterion is shown to be model selection consistent. A simulation study and a real data analysis are conducted to support theoretical findings.