Author Information

W. W. Stroup
S. D. Kachman

Abstract

Generalized linear models provide a methodology for doing regression and ANOV A-type analysis with data whose errors are not necessarily normally-distributed. Common applications in agriculture include categorical data, survival analysis, bioassay, etc. Most of the literature and most of the available computing software for generalized linear models applies to cases in which all model effects are fixed. However, many agricultural research applications lead to mixed or random effects models: split-plot experiments, animal- and plant-breeding studies, multi-location studies, etc. Recently, through a variety of efforts in a number of contexts, a general framework for generalized linear models with random effects, the "generalized linear mixed model," has been developed .

The purpose of this presentation is to present an overview of the methodology for generalized mixed linear models. Relevant background, estimating equations, and general approaches to interval estimation and hypothesis testing will be presented. Methods will be illustrated via a small data set involving binary data .

Keywords

Generalized Linear Model, Mixed Model

Creative Commons License


This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Share

COinS
 
Apr 24th, 12:30 PM

GENERALIZED LINEAR MIXED MODELS - AN OVERVIEW

Generalized linear models provide a methodology for doing regression and ANOV A-type analysis with data whose errors are not necessarily normally-distributed. Common applications in agriculture include categorical data, survival analysis, bioassay, etc. Most of the literature and most of the available computing software for generalized linear models applies to cases in which all model effects are fixed. However, many agricultural research applications lead to mixed or random effects models: split-plot experiments, animal- and plant-breeding studies, multi-location studies, etc. Recently, through a variety of efforts in a number of contexts, a general framework for generalized linear models with random effects, the "generalized linear mixed model," has been developed .

The purpose of this presentation is to present an overview of the methodology for generalized mixed linear models. Relevant background, estimating equations, and general approaches to interval estimation and hypothesis testing will be presented. Methods will be illustrated via a small data set involving binary data .