Bayesian inference on quasi-sparse count data.

Published

Journal Article

There is growing interest in analysing high-dimensional count data, which often exhibit quasi-sparsity corresponding to an overabundance of zeros and small nonzero counts. Existing methods for analysing multivariate count data via Poisson or negative binomial log-linear hierarchical models with zero-inflation cannot flexibly adapt to quasi-sparse settings. We develop a new class of continuous local-global shrinkage priors tailored to quasi-sparse counts. Theoretical properties are assessed, including flexible posterior concentration and stronger control of false discoveries in multiple testing. Simulation studies demonstrate excellent small-sample properties relative to competing methods. We use the method to detect rare mutational hotspots in exome sequencing data and to identify North American cities most impacted by terrorism.

Full Text

Duke Authors

Cited Authors

  • Datta, J; Dunson, DB

Published Date

  • December 8, 2016

Published In

Volume / Issue

  • 103 / 4

Start / End Page

  • 971 - 983

PubMed ID

  • 29422693

Pubmed Central ID

  • 29422693

Electronic International Standard Serial Number (EISSN)

  • 1464-3510

International Standard Serial Number (ISSN)

  • 0006-3444

Digital Object Identifier (DOI)

  • 10.1093/biomet/asw053

Language

  • eng