作者: Y.P Mack , M Rosenblatt
DOI: 10.1016/0047-259X(79)90065-4
关键词: Statistical physics 、 Kernel (statistics) 、 Multivariate kernel density estimation 、 k-nearest neighbors algorithm 、 Mathematics 、 Variable kernel density estimation 、 Order statistic 、 Weight function 、 Variance (accounting) 、 Multivariate statistics 、 Statistics
摘要: Abstract Under appropriate assumptions, expressions describing the asymptotic behavior of bias and variance k-nearest neighbor density estimates with weight function w are obtained. The these is compared that kernel estimates. Particular attention paid to properties in tail.