Bayesian model selection based on parameter estimates from subsamples

Jingsi Zhang, Wenxin Jiang, Xiaofeng Shao

Research output: Contribution to journalArticlepeer-review


We propose Bayesian model selection based on composite datasets, which can be constructed from various subsample estimates. The method remains consistent without fully specifying a probability model, and is useful for dependent data, when asymptotic variance of the parameter estimator is difficult to estimate.

Original languageEnglish (US)
Pages (from-to)979-986
Number of pages8
JournalStatistics and Probability Letters
Issue number4
StatePublished - Apr 2013


  • Bayes factor
  • Consistency
  • Model selection
  • Schwarz's Bayesian information criterion (BIC)
  • Self-normalization

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty


Dive into the research topics of 'Bayesian model selection based on parameter estimates from subsamples'. Together they form a unique fingerprint.

Cite this