Efficient Density Estimation using Fejer-Type Kernel Functions

It appears your Web browser is not configured to display PDF files. Download adobe Acrobat or click here to download the PDF file.

Click here to download the PDF file.

Creator: 

Kosta, Olga

Date: 

2015

Abstract: 

We consider a class of kernel-type density estimators with Fejér-type kernels and theoretical smoothing parameters. In theory, the estimator under consideration dominates in $\mathbb{L}_p$, $1\le p<\infty$, all other estimators from the literature, in the locally asymptotic minimax sense. We demonstrate via simulations that the kernel-type estimator is good by comparing its performance to other fixed kernel estimators. We also consider two empirical bandwidth selection methods, namely, the common cross-validation and the less-known method based on the Fourier analysis of kernel density estimators. The common $\mathbb{L}_2$-risk is used to assess the quality of estimation. The kernel-type estimator is then tried to real financial data for a risk measure that is widely used in many applications. The simulation results show that the theoretical estimator under study provides very good finite sample performance and the bandwidth obtained by using the Fourier analysis techniques performs better than the one from cross-validation in most settings.

Subject: 

Kernel functions
Probabilities
Statistics

Language: 

English

Publisher: 

Carleton University

Thesis Degree Name: 

Master of Science: 
M.Sc.

Thesis Degree Level: 

Master's

Thesis Degree Discipline: 

Probability and Statistics

Parent Collection: 

Theses and Dissertations

Items in CURVE are protected by copyright, with all rights reserved, unless otherwise indicated. They are made available with permission from the author(s).