Balanced samples and robust Bayesian inference in finite population sampling

Richard M. Royall*, Dany Pfeffermann

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

26 Scopus citations

Abstract

SUMMARY: Bayesian inference in finite populations uses probability models at two stages: (i) to describe relationships among population units and (ii) to express uncertainty concerning the values of parameters appearing at stage (i). Here we consider the Bayes posterior distribution of the population total when a multivariate nornxal regression model is used at stage (i), with a diffuse prior distribution on the regression coefficients. We study the situation where the stage (i) model is in error because an important regressor is omitted, and we show that in balanced samples such errors do not affect the posterior distribution. Cases where the covariance matrix contains an unknown scale parameter or is itself misspecified are also considered.

Original languageEnglish
Pages (from-to)401-409
Number of pages9
JournalBiometrika
Volume69
Issue number2
DOIs
StatePublished - Aug 1982

Keywords

  • Balanced sample
  • Bayesian inference
  • Errors in models
  • Finite population sampling
  • Prediction
  • Robust inference

Fingerprint

Dive into the research topics of 'Balanced samples and robust Bayesian inference in finite population sampling'. Together they form a unique fingerprint.

Cite this