Theory and Practice of Kernel Smoothing - habilitation thesis

KOLÁČEK, Jan. Theory and Practice of Kernel Smoothing - habilitation thesis. Brno: Neuveden, 2015, 176 pp.

Basic information

• Original name: Theory and Practice of Kernel Smoothing - habilitation thesis
• Authors: KOLÁČEK, Jan (203 Czech Republic, guarantor, belonging to the institution).
• Edition: Brno, 176 pp. 2015.
• Publisher: Neuveden

Other information

• Original language: English
• Type of outcome: Special-purpose publication
• Field of Study: 10101 Pure mathematics
• Country of publisher: Czech Republic
• Confidentiality degree: is not subject to a state or trade secret
• WWW: http://www.muni.cz/research/acad_qualif/507499
• RIV identification code: RIV/00216224:14310/15:00083745
• Organization unit: Faculty of Science
• Keywords in English: multivariate kernel regression; bandwidth matrix; kernel smoothing
• Tags: International impact, Reviewed

Abstract

Our main research interest lies in the theory of kernel smoothing. Kernel methods are well-known and intensively used by the community of nonparametricians because they are a useful tool for local weighting. Kernel estimators combine two main advantages: simple expression and ease of implementation. It is well known that the most important factor in kernel estimation is a choice of smoothing parameters. This choice is particularly important because of its role in controlling both the amount and the direction of smoothing. This problem has been widely discussed in many monographs and papers. The following overview starts with a motivation of the theory of kernel smoothing and then briefly describes the main contributions of the book [1] and the papers [2 – 10]. In order to make the presentation more compact, the thesis consists of the author’s selected papers in the area. In References one can find the list of other related publications of the author [11 – 28].