Nonlinear Multilevel Models
06 Dec 2010-pp 201-209
About: The article was published on 2010-12-06. It has received 4 citations till now. The article focuses on the topics: Restricted maximum likelihood & Maximum likelihood sequence estimation.
Citations
More filters
01 Jan 2016
TL;DR: It is suggested that multilevel techniques and associated software packages have reached the stage when they can and should be applied routinely in the analysis of social data, and that failure to do so can result in potentially serious misinterpretations.
Abstract: An introductory account is given of developments in multilevel modelling of educational and other social data. The technique is introduced with some simple examples and its importance is explained. Examples of applications in a number of areas are given, including repeated measures designs, school effective- ness studies, area-based studies and political opinion sample surveys. Almost all data collected in the social sciences have some form of inherent hierarchical structure, and this structure should be reflected in the statistical models that are used to analyse them. It is suggested that multilevel techniques and associated software packages have reached the stage when they can and should be applied routinely in the analysis of social data, and that failure to do so can result in potentially serious misinterpreta- tions.
1 citations
Dissertation•
01 Jan 2012
TL;DR: This study applied multilevel models from frequentist and Bayesian perspectives to the Swaziland Demographic and Health Survey data and showed that the INLA estimation approach is superior to the MCMC approach in Bayesian GLMMs in terms of complexity.
Abstract: Multilevel models account for different levels of aggregation that may be present in the data. Researchers are sometimes faced with the task of analysing data that are collected at different levels such that attributes about individual cases are provided as well as the attributes of groupings of these individual cases. Data with multilevel structure is common in the social sciences and other fields such as epidemiology. Ignoring hierarchies in data (where they exist) can have damaging consequences to subsequent statistical inference. This study applied multilevel models from frequentist and Bayesian perspectives to the Swaziland Demographic and Health Survey (SDHS) data. The first model fitted to the data was a Bayesian generalised linear mixed model (GLMM) using two estimation techniques: the Integrated Laplace Approximation (INLA) and Monte Carlo Markov Chain (MCMC) methods. The study aimed at identifying determinants of HIV in Swaziland and as well as comparing the different statistical models. The outcome variable of interest in this study is HIV status and it is binary, in all the models fitted the logit link was used. The results of the analysis showed that the INLA estimation approach is superior to the MCMC approach in Bayesian GLMMs in terms of com-
1 citations
Cites methods from "Nonlinear Multilevel Models"
...Equivalently, an Iterative Generalised Least Squares (IGLS) procedure can be performed, and this was proposed by Golstein [13]....
[...]
TL;DR: Two-dimensional plots to identify discordant subjects and observations in generalized linear mixed effects models, displaying discordance in two directions are presented.
Abstract: As there is an extensive body of research on diagnostics in regression models, various outlier detection methods have been developed. These methods have been extended to mixed effects models and ge...
Cites methods from "Nonlinear Multilevel Models"
...For parameter estimation in GLMM, several approaches have been proposed including maximum likelihood (ML) method [1,8,21], marginal ML method [2], pseudo-likelihood (PL) method [24], Laplace approximation [7], penalized quasi-likelihood [9,14,22], marginal quasi-likelihood [6], etc....
[...]