Skip to main content
Journal cover image

Bayesian hierarchically weighted finite mixture models for samples of distributions.

Publication ,  Journal Article
Rodriguez, A; Dunson, DB; Taylor, J
Published in: Biostatistics (Oxford, England)
January 2009

Finite mixtures of Gaussian distributions are known to provide an accurate approximation to any unknown density. Motivated by DNA repair studies in which data are collected for samples of cells from different individuals, we propose a class of hierarchically weighted finite mixture models. The modeling framework incorporates a collection of k Gaussian basis distributions, with the individual-specific response densities expressed as mixtures of these bases. To allow heterogeneity among individuals and predictor effects, we model the mixture weights, while treating the basis distributions as unknown but common to all distributions. This results in a flexible hierarchical model for samples of distributions. We consider analysis of variance-type structures and a parsimonious latent factor representation, which leads to simplified inferences on non-Gaussian covariance structures. Methods for posterior computation are developed, and the model is used to select genetic predictors of baseline DNA damage, susceptibility to induced damage, and rate of repair.

Duke Scholars

Published In

Biostatistics (Oxford, England)

DOI

EISSN

1468-4357

ISSN

1465-4644

Publication Date

January 2009

Volume

10

Issue

1

Start / End Page

155 / 171

Related Subject Headings

  • Stochastic Processes
  • Statistics & Probability
  • Sample Size
  • Regression Analysis
  • Normal Distribution
  • Models, Statistical
  • Male
  • Hydrogen Peroxide
  • Humans
  • Female
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Rodriguez, A., Dunson, D. B., & Taylor, J. (2009). Bayesian hierarchically weighted finite mixture models for samples of distributions. Biostatistics (Oxford, England), 10(1), 155–171. https://doi.org/10.1093/biostatistics/kxn024
Rodriguez, Abel, David B. Dunson, and Jack Taylor. “Bayesian hierarchically weighted finite mixture models for samples of distributions.Biostatistics (Oxford, England) 10, no. 1 (January 2009): 155–71. https://doi.org/10.1093/biostatistics/kxn024.
Rodriguez A, Dunson DB, Taylor J. Bayesian hierarchically weighted finite mixture models for samples of distributions. Biostatistics (Oxford, England). 2009 Jan;10(1):155–71.
Rodriguez, Abel, et al. “Bayesian hierarchically weighted finite mixture models for samples of distributions.Biostatistics (Oxford, England), vol. 10, no. 1, Jan. 2009, pp. 155–71. Epmc, doi:10.1093/biostatistics/kxn024.
Rodriguez A, Dunson DB, Taylor J. Bayesian hierarchically weighted finite mixture models for samples of distributions. Biostatistics (Oxford, England). 2009 Jan;10(1):155–171.
Journal cover image

Published In

Biostatistics (Oxford, England)

DOI

EISSN

1468-4357

ISSN

1465-4644

Publication Date

January 2009

Volume

10

Issue

1

Start / End Page

155 / 171

Related Subject Headings

  • Stochastic Processes
  • Statistics & Probability
  • Sample Size
  • Regression Analysis
  • Normal Distribution
  • Models, Statistical
  • Male
  • Hydrogen Peroxide
  • Humans
  • Female