Nearest neighbor classification with dependent training sequences

• 成果类型: Article
• 署名作者: Holst, M; Irle, A
• 署名单位: University of Kiel
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• 发表日期: 2001
• 页码: 1424-1442
• 关键词: DENSITY-ESTIMATION; Consistency; regression

摘要

The asymptotic classification risk for nearest neighbor procedures is well understood in the case of i.i.d. training sequences. In this article, we generalize these results to a class of dependent models including hidden Markov models. In the case where the observed patterns have Lebesgue densities, the asymptotic risk takes the same expression as in the i.i.d. case. For discrete distributions, we show that the asymptotic risk depends on the rule used for breaking ties of equal distances.