Access

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

If You Use a Screen Reader

This content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.

A Hierarchical Semiparametric Regression Model for Combining HIV-1 Phylogenetic Analyses Using Iterative Reweighting Algorithms

Li-Jung Liang and Robert E. Weiss
Biometrics
Vol. 63, No. 3 (Sep., 2007), pp. 733-741
Stable URL: http://www.jstor.org/stable/4541405
Page Count: 9
  • Read Online (Free)
  • Download ($14.00)
  • Subscribe ($19.50)
  • Cite this Item
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
A Hierarchical Semiparametric Regression Model for Combining HIV-1 Phylogenetic Analyses Using Iterative Reweighting Algorithms
Preview not available

Abstract

Phylogenetic modeling is computationally challenging and most phylogeny models fit a single phylogeny to a single set of molecular sequences. Individual phylogenetic analyses are typically performed independently using publicly available software that fits a computationally intensive Bayesian model using Markov chain Monte Carlo (MCMC) simulation. We develop a Bayesian hierarchical semiparametric regression model to combine multiple phylogenetic analyses of HIV-1 nucleotide sequences and estimate parameters of interest within and across analyses. We use a mixture of Dirichlet processes as a prior for the parameters to relax inappropriate parametric assumptions and to ensure the prior distribution for the parameters is continuous. We use several reweighting algorithms for combining completed MCMC analyses to shrink parameter estimates while adjusting for data set-specific covariates. This avoids constructing a large complex model involving all the original data, which would be computationally challenging and would require rewriting the existing stand-alone software.

Page Thumbnails

  • Thumbnail: Page 
733
    733
  • Thumbnail: Page 
734
    734
  • Thumbnail: Page 
735
    735
  • Thumbnail: Page 
736
    736
  • Thumbnail: Page 
737
    737
  • Thumbnail: Page 
738
    738
  • Thumbnail: Page 
739
    739
  • Thumbnail: Page 
740
    740
  • Thumbnail: Page 
741
    741