Sampling schemes for generalized linear Dirichlet process random effects models
- 170 Downloads
We evaluate MCMC sampling schemes for a variety of link functions in generalized linear models with Dirichlet process random effects. First, we find that there is a large amount of variability in the performance of MCMC algorithms, with the slice sampler typically being less desirable than either a Kolmogorov–Smirnov mixture representation or a Metropolis–Hastings algorithm. Second, in fitting the Dirichlet process, dealing with the precision parameter has troubled model specifications in the past. Here we find that incorporating this parameter into the MCMC sampling scheme is not only computationally feasible, but also results in a more robust set of estimates, in that they are marginalized-over rather than conditioned-upon. Applications are provided with social science problems in areas where the data can be difficult to model, and we find that the nonparametric nature of the Dirichlet process priors for the random effects leads to improved analyses with more reasonable inferences.
KeywordsLinear mixed models Generalized linear mixed models Hierarchical models Gibbs sampling Metropolis–Hastings algorithm Slice sampling
Unable to display preview. Download preview PDF.
- Abramowitz M, Stegun IA (1972) Stirling numbers of the second kind. Section 24.1.4. In: Handbook of mathematical functions with formulas, graphs, and mathematical tables, 9th printing. Dover, New York, pp 824–825.Google Scholar
- Chib S, Greenberg E, Chen Y (1998) MCMC methods for fitting and comparing multinomial response models. Technical Report, Economics Working Paper Archive, Washington University at St. Louis, http://18.104.22.168/econ-wp/em/papers/9802/9802001.pdf
- Dorazio RM, Mukherjee B, Zhang L, Ghosh M, Jelks HL, Jordan F (2007) Modelling unobserved sources of heterogeneity in animal abundance using a Dirichlet process prior. Biometrics (online publication August 3, 2007)Google Scholar
- Gurr TR, Marshall MG, Jaggers K (2003) PolityIV, http://www.cidcm.umd.edu/inscr/polity/
- Kyung M, Gill J, Casella G (2011) New findings from terrorism data: Dirichlet process random effects models for latent groups. J R Stat Soc Ser C (Forthcoming)Google Scholar