Optimal convergence rates of nonparametric conditional quantiles in dependent cases  

作　　者：施沛德 何旭铭 

机构地区：[1]Peking University, Beijing 100871, China [2]University of Illinois, USA

出　　处：《Chinese Science Bulletin》1995年第8期627-631,共5页

基　　金：Project supported in part by a postdoctoral fellowship and the National Natural Science Foundation of China.

摘　　要：The ordinary quantiles for univariate data were successfully generalized to linear modelsin Koenker and Bassett. Regression quantiles provide more specific and more global in-formation on the relationship of two variables through their distributions. Mosteller andTukey argued that the use of regression quantiles helps to provide a more complete pic-

关 键 词：NONPARAMETRIC regression QUANTILES B-SPLINES optimal rates of convergence STRICTLY STATIONARY sequence β-mixing. 

分 类 号：O211[理学—概率论与数理统计]