Article |
Nonparametric Bayes local partition models for random effects
Department of Statistical Science, Box 90251, Duke University, Durham, North Carolina 27708, U.S.A. dunson{at}stat.duke.edu
Received for publication 1 February 2008. Revision received 1 November 2008.
This paper focuses on the problem of choosing a prior for an unknown random effects distribution within a Bayesian hierarchical model. The goal is to obtain a sparse representation by allowing a combination of global and local borrowing of information. A local partition process prior is proposed, which induces dependent local clustering. Subjects can be clustered together for a subset of their parameters, and one learns about similarities between subjects increasingly as parameters are added. Some basic properties are described, including simple two-parameter expressions for marginal and conditional clustering probabilities. A slice sampler is developed which bypasses the need to approximate the countably infinite random measure in performing posterior computation. The methods are illustrated using simulation examples, and an application to hormone trajectory data.
Key Words: Dirichlet process • Functional data • Local shrinkage • Meta-analysis • Multi-task learning • Partition model • Slice sampling • Stick-breaking
References
-
Bigelow J. L., Dunson D. B. Bayesian semiparametric joint models for functional predictors. J. Am. Statist. Assoc. (2009) 104:26–36.[CrossRef][Web of Science]
Bush C. A., MacEachern S. N. A semiparametric Bayesian model for randomised block designs. Biometrika (1996) 83:275–85.
Cifarelli D. M., Regazzini E. Nonparametric statistical problems under partial exchangeability: The use of associative means (in italian). Annali del'Instituto di Matematica Finianziara dell'Universitá di Torino, Serie III (1978) 12:1–36.
De Iorio M., Müller P., Rosner G., MacEachern S. N. An ANOVA model for dependent random measures. J. Am. Statist. Assoc. (2004) 99:205–15.[CrossRef][Web of Science]
Dunson D. B., Xue Y., Carin L. The matrix stick-breaking process: Flexible Bayes meta analysis. J. Am. Statist. Assoc. (2008) 103:317–27.[CrossRef][Web of Science]
Ferguson T. S. A Bayesian analysis of some nonparametric problems. Ann. Statist. (1973) 1:209–30.[CrossRef]
Ferguson T. S. Prior distributions on spaces of probability measures. Ann. Statist. (1974) 2:615–29.[CrossRef]
Heard N. A., Holmes C. C., Stephens D. A. A quantitative study of gene regulation involved in the immune response of anopheline mosquitoes: An application of Bayesian hierarchical clustering of curves. J. Am. Statist. Assoc. (2006) 101:18–29.[CrossRef][Web of Science]
Ishwaran H., James L. F. Gibbs sampling methods for stick-breaking priors. J. Am. Statist. Assoc. (2001) 96:161–73.[CrossRef][Web of Science]
MacEachern S. N. Dependent nonparametric processes. Proc. Sect. Bayesian Statist. Sci. (1999) Alexandria, VA: American Statistical Association. 50–55.
Müller P., Rosner G. L. A Bayesian population model with hierarchical mixture priors applied to blood count data. J. Am. Statist. Assoc. (1997) 92:1279–92.[CrossRef][Web of Science]
Papaspiliopoulos O., Roberts G. O. Retrospective MCMC for Dirichlet process hierarchical models. Biometrika (2008) 95:169–86.
Pitman J., Yor M. The two parameter Poisson–Dirichlet distribution derived from a stable subordinator. Ann. Prob. (1997) 25:855–900.[CrossRef]
Sethuraman J. A constructive definition of Dirichlet priors. Statist. Sinica (1994) 4:639–50.
Walker S. G. Sampling the Dirichlet mixture model with slices. Comm. Statist. (2007) B 36:45–54.
Wilcox A., Weinberg C. R., O'Connor J., Baird D., Schlatterer J., Canfield R., Armstrong E., Nisula B. Incidence of early loss of pregnancy. New Engl. J. Med. (1988) 319:189–94.[Abstract]
CiteULike 
Connotea 
Del.icio.us What's this?
| ||||||||||||||||||||||||||||||||||||||||||||||