EXACT MULTIVARIATE BAYESIAN BOOTSTRAP DISTRIBUTIONS OF MOMENTS

• 成果类型: Article
• 署名作者: GASPARINI, M
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• DOI: 10.1214/aos/1176324620
• 发表日期: 1995
• 页码: 762-768
• 关键词: splines

摘要

The common unknown probability law P of a random sample Y-1,..., Y-n is assigned a Dirichlet process prior with index alpha. It is shown that the posterior joint density of several moments of P converges, as alpha(R) --> 0, to a multivariate B-spline, which is, therefore, the Bayesian bootstrap joint density of the moments. The result provides the basis for possible default nonparametric Bayesian inference on unknown moments.