Generalized Linear Mixed-Effects Models in R
Small Business Information
Suite A, 75 Aero Camino, Goleta, CA, 93117
AbstractNot Available "The Nonlinear and Linear Mixed-Effects (NLME) package for the open source statistical software system R provides an effective and efficient way to analyze longitudinal data collected from nested groups of subjects when the response of interest is on acontinuous scale. At present it does not provide methods for analyzing binary, multinomial, or ordinal responses. There are some functions in other R packages, such as the glmmPQL function in the MASS package and the glmm function in the GLMMGibbspackage, that can fit a generalized linear mixed model suitable for binary responses. Models for multinomial or ordinal responses are not yet as well defined as models for binary responses.For Phase 1 we will concentrate on enhancing the R implementation of the generalized linear mixed model, beginning with the glmmPQL approach but allowing for later extensions to more accurate approaches (e.g., Adaptive Gaussian Quadrature). We will use aset of simulated data sets described by Rodriguez and Goldman (1995, 2001) to test and validate the toolbox. We will evaluate different approaches to modeling ordinal and multinomial data, the theory of which is less well developed than that of binomialdata, and identify methods for implementing the approaches in the toolbox. The successful completion of this research will result in extensions to the NLME package for R that will enable statisticians and analysts to build generalized linear mixed-effectsmodels for binary and ordinal data, especially longitudinal data."
* information listed above is at the time of submission.