✦ LIBER ✦

Generalized linear mixed models for meta-analysis

✍ Scribed by Robert W. Platt; Brian G. Leroux; Norman Breslow

Publisher: John Wiley and Sons
Year: 1999
Tongue: English
Weight: 134 KB
Volume: 18
Category: Article
ISSN: 0277-6715
DOI: 10.1002/(sici)1097-0258(19990330)18:6<643::aid-sim76>3.0.co;2-m

No coin nor oath required. For personal study only.

✦ Synopsis

We examine two strategies for meta-analysis of a series of 2;2 tables with the odds ratio modelled as a linear combination of study level covariates and random effects representing between-study variation. Penalized quasi-likelihood (PQL), an approximate inference technique for generalized linear mixed models, and a linear model fitted by weighted least squares to the observed log-odds ratios are used to estimate regression coefficients and dispersion parameters. Simulation results demonstrate that both methods perform adequate approximate inference under many conditions, but that neither method works well in the presence of highly sparse data. Under certain conditions with small cell frequencies the PQL method provides better inference.

📜 SIMILAR VOLUMES

Meta-analysis by random effect modelling

Meta-analysis by random effect modelling in generalized linear models

✍ Murray Aitkin 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 94 KB 👁 1 views

The meta-analysis of multi-centre trials can be based on either "xed or random e!ect models. This paper argues for the general use of random e!ect models, and illustrates the value of non-parametric maximum likelihood (NPML) analysis of such trials. The same general approach uni"es administrative &l

An Introduction to Categorical Data Anal

An Introduction to Categorical Data Analysis || Random Effects: Generalized Linear Mixed Models

✍ Agresti, Alan 📂 Article 📅 2007 🏛 John Wiley & Sons, Inc. 🌐 English ⚖ 314 KB 👁 1 views

**Praise for the First Edition** "This is a superb text from which to teach categorical data analysis, at a variety of levels. . . [t]his book can be very highly recommended." —*Short Book Reviews* "Of great interest to potential readers is the variety of fields that are represented in the examp

Residuals analysis of the generalized li

Residuals analysis of the generalized linear models for longitudinal data

✍ Yue-Cune Chang 📂 Article 📅 2000 🏛 John Wiley and Sons 🌐 English ⚖ 196 KB 👁 2 views

The generalized estimation equation (GEE) method, one of the generalized linear models for longitudinal data, has been used widely in medical research. However, the related sensitivity analysis problem has not been explored intensively. One of the possible reasons for this was due to the correlated

A robust mixed linear model analysis for

A robust mixed linear model analysis for longitudinal data

✍ Paramjit S. Gill 📂 Article 📅 2000 🏛 John Wiley and Sons 🌐 English ⚖ 124 KB 👁 2 views

This paper describes robust procedures for estimating parameters of a mixed e!ects linear model as applied to longitudinal data. In addition to "xed regression parameters, the model incorporates random subject e!ects to accommodate between-subjects variability and autocorrelation for within-subject

Multivariate linear mixed models for mul

Multivariate linear mixed models for multiple outcomes

✍ Mary Sammel; Xihong Lin; Louise Ryan 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 171 KB 👁 1 views

We propose a multivariate linear mixed (MLMM) for the analysis of multiple outcomes, which generalizes the latent variable model of Sammel and Ryan. The proposed model assumes a #exible correlation structure among the multiple outcomes, and allows a global test of the impact of exposure across outco

A semi-parametric Bayesian approach to g

A semi-parametric Bayesian approach to generalized linear mixed models

✍ Ken P. Kleinman; Joseph G. Ibrahim 📂 Article 📅 1998 🏛 John Wiley and Sons 🌐 English ⚖ 170 KB 👁 2 views

The linear mixed effects model with normal errors is a popular model for the analysis of repeated measures and longitudinal data. The generalized linear model is useful for data that have non-normal errors but where the errors are uncorrelated. A descendant of these two models generates a model for