Inverse Gaussian model for small area estimation via Gibbs sampling

  • Fassil Nebebe Department of Decision Sciences and MIS, Concordia University, Montréal, Québec H3G 1M8 Canada
  • Cynthia M DeSouza Medtronic, Inc., MS T278, Tachy Clinical Division, Minneapolis, MN 55432 USA
  • Yogendra P Chaubey Department of Mathematics and Statistics, Concordia University, Montréal, Québec H4B 1R6 Canada
Keywords: Finite population sampling, hierarchical Bayesian inference, lognormal model, MCMC integration, shrinkage estimates

Abstract

We present a Bayesian method for estimating small area parameters under an inverse Gaussian model. The method is extended to estimate small area parameters for finite populations. The Gibbs sampler is proposed as a mechanism for implementing the Bayesian paradigm. We illustrate the method by application to household income survey data, comparing it against the usual lognormal model for positively skewed data.

Key words/phrases: Finite population sampling, hierarchical Bayesian inference, lognormal model, MCMC integration, shrinkage estimates

SINET: Ethiopian Journal of Science Vol. 28 (1) 2005: 1–14
Published
2005-10-14
Section
Articles

Journal Identifiers


eISSN: 2520–7997
print ISSN: 0379-2897