Template-type: ReDIF-Paper 1.0
Author-Name: Vitaliy Oryshchenko
Author-Workplace-Name: Department of Economics, University of Oxford 
Author-Email:vitaliy.oryshchenko@economics.ox.ac.uk
Author-Name: Richard J. Smith
Author-Workplace-Name: UCL, IFS and University of Cambridge
Title: Generalised empirical likelihood-based kernel density estimation
Abstract: If additional information about the distribution of a random variable is available in the form of moment conditions,
a weighted kernel density estimate re
ecting the extra information can be constructed by replacing the
uniform weights with the generalised empirical likelihood probabilities. It is shown that the resultant density
estimator provides an improved approximation to the moment constraints. Moreover, a reduction in variance is
achieved due to the systematic use of the extra moment information.
Classification-JEL: C14
Keywords: weighted kernel density estimation, moment conditions, higher-order expansions, normal mixtures.
Length: 46 pages
Creation-Date: 2013-02-12
Number: 2013-W03
File-URL: http://www.nuffield.ox.ac.uk/Academic/Economics/Working%20Papers/Documents/2013/gelkde_wp_Jan13.pdf
File-Format: application/pdf
Handle: RePEc:nuf:econwp:1303