Efficient and accurate approximate Bayesian inference with an application to insurance data

George Streftaris, Bruce J. Worton

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)


Efficient and accurate Bayesian Markov chain Monte Carlo methodology is proposed for the estimation of event rates under an overdispersed Poisson distribution. An approximate Gibbs sampling method and an exact independence-type Metropolis-Hastings algorithm are derived, based on a log-normal/gamma mixture density that closely approximates the conditional distribution of the Poisson parameters. This involves a moment matching process, with the exact conditional moments obtained employing an entropy distance minimisation (Kullback-Liebler divergence) criterion. A simulation study is conducted and demonstrates good Bayes risk properties and robust performance for the proposed estimators, as compared with other estimating approaches under various loss functions. Actuarial data on insurance claims are used to illustrate the methodology. The approximate analysis displays superior Markov chain Monte Carlo mixing efficiency, whilst providing almost identical inferences to those obtained with exact methods. © 2007 Elsevier B.V. All rights reserved.

Original languageEnglish
Pages (from-to)2604-2622
Number of pages19
JournalComputational Statistics and Data Analysis
Issue number5
Publication statusPublished - 20 Jan 2008


  • Bayes risk
  • Effective sample size
  • Entropy distance
  • Hierarchical Bayesian analysis
  • Insurance claims
  • Markov chain Monte Carlo
  • Mixture distribution
  • Monte Carlo error


Dive into the research topics of 'Efficient and accurate approximate Bayesian inference with an application to insurance data'. Together they form a unique fingerprint.

Cite this