Distribution-free consistency of kernel non-parametric M-estimators | Macquarie University ResearchOnline

Home

Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.14/10019

28 Visitors

31 Hits

0 Downloads

Title: Distribution-free consistency of kernel non-parametric M-estimators
Related: Statistics & probability letters, Vol. 58, Issue 4, p.343-353
DOI: 10.1016/S0167-7152(02)00106-2
Publisher: Elsevier
Date: 2002
Author/Creator: Kozek, Andrzej S
Author/Creator: Pawlak, Mirosław
Description: We prove that in the case of independent and identically distributed randomvectors (X_i; Y_i) a class of kernel type M-estimators is universally and strongly consistent for conditional M-functionals. The term universal means that the strong consistency holds for all joint probability distributions of (X; Y ). The conditional M-functional minimizes (2.2) for almost every x. In the case M(y) = |y| the conditional M-functional coincides with the L₁-functional and with the conditional median.
Description: 11 page(s)
Resource Type: journal article
Organisation: Macquarie University. Dept. of Statistics

Macquarie University ResearchOnline