The Extension of REML Algorithm for Hierarchical Generalized Linear Models

• 발행기관: 한국자료분석학회
• 저자명: Maengseok Noh
• 간행물 정보: 『Journal of The Korean Data Analysis Society (JKDAS)』Vol.16 No.3, 1159~1170쪽, 전체 12쪽
• 주제분류: 자연과학 > 통계학
• 파일형태: PDF
• 발행일자: 2014.06.30

영문 초록

The restricted maximum likelihood procedure is useful for inferences about variance components in mixed linear models. However, its extension to hierarchical generalized linear models has encountered some difficulties. Numerical integration such as Gauss-Hermite quadrature is generally not recommended when the dimensionality of the integral is high. Approximate methods such as penalized quasi-likelihood estimators may have severe biases when analysing binary data. In this paper we introduce the hierarchical likelihood (or h-likelihood) algorithm which resolves these difficulties. Numerical studies show how the proposed method overcomes them. We also discuss how the restricted maximum likelihood estimating equations for mixed linear models can be modified in more general models.

목차

1. Introduction

2. Model and method

3. REML procedure for HGLMs

4. Numerical studies

5. Conclusions

References

키워드

Generalized linear mixed models Hierarchical generalized linear models Restricted maximum likelihood Hierarchical likelihood