STATISTICAL-INFERENCE FOR CONDITIONAL CURVES - POISSON-PROCESS APPROACH
成果类型：
Article
署名作者：
FALK, M; REISS, RD
署名单位：
Universitat Siegen
刊物名称：
ANNALS OF STATISTICS
ISSN/ISSBN：
0090-5364
DOI：
10.1214/aos/1176348656
发表日期：
1992
页码：
779-796
关键词：
摘要：
A Poisson approximation of a truncated, empirical point process enables us to reduce conditional statistical problems to unconditional ones. Let (X, Y) be a (d + m)-dimensional random vector and denote by F(.\x) the conditional d.f. of Y given X = x. Applying our approach, one may study the fairly general problem of evaluating a functional parameter T(F(.\x1),...,F(.\x(p)) based on independent replicas (X1, Y1),..., (X(n), Y(n)) of (X, Y). This will be exemplified in the particular cases of nonparametric estimation of regression means and regression quantiles besides other functionals.