TY - JOUR UR - http://lib.ugent.be/catalog/pug01:8197080 ID - pug01:8197080 LA - eng TI - A review of R-packages for random-intercept probit regression in small clusters PY - 2016 JO - (2016) FRONTIERS IN APPLIED MATHEMATICS AND STATISTICS SN - 2297-4687 PB - 2016 AU - Josephy, Haeike PP01 002003374241 AU - Loeys, Tom PP01 801001085043 0000-0003-4551-5502 AU - Rosseel, Yves PP01 PP54 801000974909 0000-0002-4129-4477 AB - Generalized Linear Mixed Models (GLMMs) are widely used to model clustered categorical outcomes. To tackle the intractable integration over the random effects distributions, several approximation approaches have been developed for likelihood-based inference. As these seldom yield satisfactory results when analyzing binary outcomes from small clusters, estimation within the Structural Equation Modeling (SEM) framework is proposed as an alternative. We compare the performance of R-packages for random-intercept probit regression relying on: the Laplace approximation, adaptive Gaussian quadrature (AGQ), Penalized Quasi-Likelihood (PQL), an MCMC-implementation, and integrated nested Laplace approximation within the GLMM-framework, and a robust diagonally weighted least squares estimation within the SEM-framework. In terms of bias for the fixed and random effect estimators, SEM usually performs best for cluster size two, while AGQ prevails in terms of precision (mainly because of SEM's robust standard errors). As the cluster size increases, however, AGQ becomes the best choice for both bias and precision. ER -Download RIS file
00000nam^a2200301^i^4500 | |||
001 | 8197080 | ||
005 | 20161219154801.0 | ||
008 | 161129s2016------------------------eng-- | ||
022 | a 2297-4687 | ||
024 | a 1854/LU-8197080 2 handle | ||
024 | a 10.3389/fams.2016.00018 2 doi | ||
040 | a UGent | ||
245 | a A review of R-packages for random-intercept probit regression in small clusters | ||
260 | c 2016 | ||
520 | a Generalized Linear Mixed Models (GLMMs) are widely used to model clustered categorical outcomes. To tackle the intractable integration over the random effects distributions, several approximation approaches have been developed for likelihood-based inference. As these seldom yield satisfactory results when analyzing binary outcomes from small clusters, estimation within the Structural Equation Modeling (SEM) framework is proposed as an alternative. We compare the performance of R-packages for random-intercept probit regression relying on: the Laplace approximation, adaptive Gaussian quadrature (AGQ), Penalized Quasi-Likelihood (PQL), an MCMC-implementation, and integrated nested Laplace approximation within the GLMM-framework, and a robust diagonally weighted least squares estimation within the SEM-framework. In terms of bias for the fixed and random effect estimators, SEM usually performs best for cluster size two, while AGQ prevails in terms of precision (mainly because of SEM's robust standard errors). As the cluster size increases, however, AGQ becomes the best choice for both bias and precision. | ||
598 | a A2 | ||
100 | a Josephy, Haeike u PP01 0 002003374241 0 802001284375 | ||
700 | a Loeys, Tom u PP01 0 801001085043 0 0000-0003-4551-5502 | ||
700 | a Rosseel, Yves u PP01 u PP54 0 801000974909 0 0000-0002-4129-4477 | ||
650 | a Mathematics and Statistics | ||
653 | a Structural Equation Modeling | ||
653 | a Monte Carlo studies | ||
653 | a Mixed models | ||
653 | a Categorical Data Analysis | ||
653 | a Multilevel Modeling | ||
773 | t FRONTIERS IN APPLIED MATHEMATICS AND STATISTICS g Front. Appl. Math. Stat. 2016. 2 (18) p.1-13 q 2:18<1 | ||
856 | 3 Full Text u https://biblio.ugent.be/publication/8197080/file/8197180 z [open] y fams-02-00018.pdf | ||
920 | a article | ||
852 | x PP b PP01 | ||
922 | a UGENT-PP |
All data below are available with an Open Data Commons Open Database License. You are free to copy, distribute and use the database; to produce works from the database; to modify, transform and build upon the database. As long as you attribute the data sets to the source, publish your adapted database with ODbL license, and keep the dataset open (don't use technical measures such as DRM to restrict access to the database).
The datasets are also available as weekly exports.