On a Posterior Predictive Density Sample Size Criterion
Theodoros Nicoleris, Stephen Graham Walker · Scandinavian Journal of Statistics · 2006
Abstract. Let Ω be a space of densities with respect to someσ‐finite measureμand letΠbe a prior distribution having support Ω with respect to some suitable topology. Conditional onf, letXn = (X1 ,…, Xn) be an independent and identically distributed sample of sizenfromf. This paper introduces a Bayesian non‐parametric criterion for sample size determination which is based on the integrated squared distance between posterior predictive densities. An expression for the sample size is obtained when the prior is a Dirichlet mixture of normal densities.