An exponential partial prior for improving nonparametric maximum likelihood estimation in mixture models

Jiping Wang*, Bruce G. Lindsay

*Corresponding author for this work

Research output: Contribution to journalArticle

14 Scopus citations

Abstract

Given observations originating from a mixture distribution f [x ; Q (λ)] where the kernel f is known and the mixing distribution Q is unknown, we consider estimating a functional θ (Q) of Q. A natural estimator of such a functional can be obtained by substituting Q with its nonparametric maximum likelihood estimator (NPMLE), denoted here as over(Q, ̂). We demonstrate however, that the plug-in estimator θ (over(Q, ̂)) can be unstable or substantially biased due to large variability of over(Q, ̂) or structural properties of the parameter space of λ. In this paper we propose using a partial prior for Q to improve the estimation in motivating examples. In particular we propose an empirical Bayes estimation method based on an exponential prior, and show its effectiveness in improving estimation in motivating examples of binomial mixture.

Original languageEnglish (US)
Pages (from-to)30-45
Number of pages16
JournalStatistical Methodology
Volume5
Issue number1
DOIs
StatePublished - Jan 1 2008

    Fingerprint

Keywords

  • Empirical Bayes
  • NPMLE
  • Partial prior
  • Penalized NPMLE

ASJC Scopus subject areas

  • Statistics and Probability

Cite this