Nonclassical parameters in kernel estimation

Abstract

In kernel method, using in estimation as well as in hypothesis testing problems, two parameters should be fixed: kernel function and smoothing parameter. Some methods of kernel estimation and methods of choosing kernel parameters (classical and nonclassical) are presented. Basing on simulation study results, chosen kernel estimation methods are compared, taking into account their properties.

Authors and Affiliations

Aleksandra Baszczyńska

Keywords

Related Articles

On the differential subordination of harmonic mean to a linear function / O podporządkowaniu różniczkowym średniej harmonicznej funkcji liniowej

In this paper we examine the differential subordination related to the harmonic mean. For a dominant being a linear function we improve the general result of [?].

Some noncommutative rings constructed on the base of polynomials x² + tx + 1 and their zero divisors

For any Galois field F = GF(pn) we construct some ring extension R(F) of order p4n. Such construction may be applied also for any infinite field F with char F 6= 0. Then, for any element of R(F) we give necessary and suf...

Some estimations of the Łojasiewicz exponent for polynomial mappings on semialgebraic sets / Pewne szacowania wykładnika Łojasiewicza dla odwzorowań wielomianowych na zbiorach semialgebraicznych

We strengthen some estimations of the local and global Lojasiewicz exponent for polynomial mappings on closed semialgebraic sets obtained by K. Kurdyka, S. Spodzieja and A. Szlachcińska in [4].

Download PDF file
  • EP ID EP191296
  • DOI -
  • Views 79
  • Downloads 0

How To Cite

Aleksandra Baszczyńska (2016). Nonclassical parameters in kernel estimation. Bulletin de la Société des sciences et des lettres de Łódź, Série: Recherches sur les déformations, 0(1), 135-148. https://europub.co.uk/articles/-A-191296