Bayes modal estimation

For the first time in gllamm's history (which began in 1998), we have grant funding to support gllamm development. As part of a joint project with Andrew Gelman and Jingchen Liu at Columbia University, gllamm will become a little bit Bayesian. We will allow the user to specify weakly informative priors for the variance-covariance matrices of the random effects (or latent variables) to avoid estimates on the boundary.

Papers:

Chung, Y., Rabe-Hesketh, S., Gelman A., Dorie, V. and Liu, J. (2013a). A nondegenerate penalized likelihood estimator for variance parameters in multilevel models. Psychometrika 78 (4), 685-709. get

Chung, Y., Rabe-Hesketh, S. and Choi, I.-H. (2013b). Avoiding zero between-study variance estimates in random-effects meta-analysis. Statistics in Medicine 32 (23), 4071-4089. get

Chung, Y., Gelman, A., Rabe-Hesketh, S., Liu, S. and Dorie, V. (submitted). Weakly informative prior for point estimation of covriance matrices in hierarchical linear models.

gllamm code for gamma prior for random-intercept variance/standard deviation

• Install the latest version of gllamm (Sept 7, 2011)
• download init_prior.ado and calc_prior.ado
• copy these files into your working directory (or anywhere in adopath)

Examples

• Random-effects meta-analyses and meta-regressions
  • SAT coaching (8-schools) data
    run do-file with 8-schools data to get results from Table 1 in Chung et al. (2013a)
  • Teacher expectancy data
    Run do-file to obtain the results described in this document which accompanies the paper Chung et al. (2013b)
  • Exercise for depression data
    Run do-file with these data to get results from Table 1 in Chung et al. (2013b)
  • Antiplatelet therapy data
    Run do-file with these data to get results from Sections 2.2 and 7 in Chung et al. (2013b)
• Cluster-randomized studies
  • Dietary supplements in Kenyan schools
    Run do-file to get results from Table 2 in Chung et al. (2013a)

See also blme code in R by Vincent Dorie

Grant:
2010-2013 Gelman, A., Rabe-Hesketh, S., and Liu, J. Practical Tools for Multilevel/Hierarchical Modeling in Education Research. U.S. Department of Education, Institute of Education Sciences (IES). Grant R305D100017.