On a nonparametric recursive estimator of the mixing distribution

On a nonparametric recursive estimator of the mixing distribution

Michael A. Newton .

To appear Sankhya

First issued August 2000 as Technical Report 1021, Department of Statistics, University of Wisconsin, Madison.

Abstract:


Routinely in statistical applications hierarchical models arise in which unobserved random effects contribute to heterogeneity amongst sampling units. An easily computable, smooth nonparametric estimate of the underlying mixing distribution can be derived as an approximate nonparametric Bayes estimate under a Dirichlet process prior. I discuss the recursive estimation algorithm, its consistency properties, and its application in several examples, including its use as a model diagnostic in the analysis of DNA microarray gene expression data.

Accepted Version, 12/01
Original Technical Report, 8/00