Nonhomogeneity analysis using borrowed strength

• 成果类型: Article
• 署名作者: Priebe, CE
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.2307/2291575
• 发表日期: 1996
• 页码: 1497-1503
• 关键词: change-point estimation; CLASSIFICATION; relaxation; tissue

摘要

This article develops a ''borrowed strength'' methodology for estimating local probability densities in a random field. Under a piecewise stationarity condition similarities between the densities in different regions of the field can be exploited by estimating a global mixture density and imposing the parameter-space support of this borrowed strength estimate on the local estimation problems. The local estimates are then used in an analysis of the homogeneity of the field, which is shown to benefit from the method of borrowing strength.