User Tools

Site Tools


Statistics Seminar
Department of Mathematical Sciences

DATE:Thursday, February 18, 2016
TIME:1:15pm to 2:15pm
SPEAKER:Anton Schick, Binghamton University
TITLE:Convergence rates of kernel density estimators in the $L_1$ norm


The usual approach to evaluate the performance of a kernel density estimator (KDE) is to look at the mean integrated square error. This provides rates of convergence in the $L_2$-norm. In this talk rates of convergence in the $L_1$-norm are presented. We consider both estimators of a density $f$ and its convolution $f*f$ with itself. In the former case the rates are nonparametric $n^{-s/(2s+1)}$ and depend on the smoothness $s$ of $f$. In the second case we obtain the parametric rate $n^{-1/2}$.

seminars/stat/160218.txt · Last modified: 2016/05/01 21:47 by aleksey