OPTIMAL ESTIMATION OF VARIANCE IN NONPARAMETRIC REGRESSION WITH RANDOM DESIGN

• 成果类型: Article
• 署名作者: Shen, Yandi; Gao, Chao; Witten, Daniela; Han, Fang
• 署名单位: University of Washington; University of Washington Seattle; University of Chicago
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• DOI: 10.1214/20-AOS1944
• 发表日期: 2020
• 页码: 3589-3618
• 关键词: square successive difference; optimal adaptive estimation; efficient estimation; derivatives; functionals; covariate; bounds; rates; ratio

摘要

Consider the heteroscedastic nonparametric regression model with random design Y-i = f (X-i) + V-1/2 (X-i)epsilon(i), i = 1, 2, ..., n, with f (.) and V (.) alpha- and beta-Holder smooth, respectively. We show that the minimax rate of estimating V (.) under both local and global squared risks is of the order n( - 8 alpha beta/4 alpha beta+2 alpha+beta )boolean OR n (- 2 beta/2 beta+1), where a boolean OR b := max{a, b} for any two real numbers a, b. This result extends the fixed design rate n(-4 alpha) boolean OR n(-2 beta/(2 beta+1)) derived in (Ann. Statist. 36 (2008) 646-664) in a nontrivial manner, as indicated by the appearances of both a and beta in the first term. In the special case of constant variance, we show that the minimax rate is n(-8 alpha/(4a+1))boolean OR n(-1) for variance estimation, which further implies the same rate for quadratic functional estimation and thus unifies the minimax rate under the nonparametric regression model with those under the density model and the white noise model. To achieve the minimax rate, we develop a U-statistic-based local polynomial estimator and a lower bound that is constructed over a specified distribution family of randomness designed for both epsilon(i) and X-i.