Search

Finite mixture models are flexible parametric models that allow one to describe complex probability distributions as a mixture of a small number of simple probability distributions. Measures of health status are often used to reflect a person's overall health. Such measures may be subject to a ceiling effect, in that the measure is unable to discern gradations in health status above the ceiling. The purpose of this paper is to illustrate the use of finite mixture models to describe the probability distribution of the Health Utilities Index, under the assumption that the HUI is subject to a ceiling effect. Mixture models with two through six components are fit to the HUI. Bayes factors were used to compare the evidence that the Canadian population of non-institutionalized residents is composed of four distinct subpopulations, and that a mixture of six Normal components is required to describe these four subpopulations. [ABSTRACT FROM AUTHOR]

We describe and illustrate Bayesian inference in models for density estimation using mixtures of Dirichlet processes. These models provide natural settings for density estimation and are exemplified by special cases where data are modeled as a sample from mixtures of normal distributions. Efficient simulation methods are used to approximate various prior, posterior, and predictive distributions. This allows for direct inference on a variety of practical issues, including problems of local versus global smoothing, uncertainty about density estimates, assessment of modality, and the inference on the numbers of components. Also, convergence results are established for a general class of normal mixture models. [ABSTRACT FROM AUTHOR]