A RELIABLE DATA-BASED BANDWIDTH SELECTION METHOD FOR KERNEL DENSITY-ESTIMATION

• 成果类型: Article
• 署名作者: SHEATHER, SJ; JONES, MC
• 署名单位: International Business Machines (IBM); IBM USA; University of New South Wales Sydney
• 刊物名称: JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY
• ISSN/ISSBN: 1369-7412
• 发表日期: 1991
• 页码: 683-690
• 关键词: data-based algorithm; window width; point

摘要

We present a new method for data-based selection of the bandwidth in kernel density estimation which has excellent properties. It improves on a recent procedure of Park and Marron (which itself is a good method) in various ways. First, the new method has superior theoretical performance; second, it also has a computational advantage; third, the new method has reliably good performance for smooth densities in simulations, performance that is second to none in the existing literature. These methods are based on choosing the bandwidth to (approximately) minimize good quality estimates of the mean integrated squared error. The key to the success of the current procedure is the reintroduction of a nonstochastic term which was previously omitted together with use of the bandwidth to reduce bias in estimation without inflating variance.