On sequential designs in nonlinear problems

• 成果类型: Article
• 署名作者: Hu, I
• 署名单位: Hong Kong University of Science & Technology
• 刊物名称: BIOMETRIKA
• ISSN/ISSBN: 0006-3444
• DOI: 10.1093/biomet/85.2.496
• 发表日期: 1998
• 页码: 496503
• 关键词: regression-models; inference

摘要

In this paper we study the consistency of parameter estimators in sequential nonlinear design. Our main tool is a recursion which holds for the sequence of posterior variances. Under mild conditions, we establish the strong consistency of Bayes estimators in stochastic regression models which cover a broad range of nonlinear problems. Four examples from nonlinear sequential design are discussed.