Nonparametric estimation of multivariate scale mixtures of uniform densities

From MaRDI portal
Publication:413749

DOI10.1016/J.JMVA.2012.01.001zbMATH Open1352.62049arXiv1005.1352OpenAlexW2049949770WikidataQ42558027 ScholiaQ42558027MaRDI QIDQ413749FDOQ413749


Authors: Marios G. Pavlides, Jon A. Wellner Edit this on Wikidata


Publication date: 7 May 2012

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Abstract: Suppose that mU=(U1,ldots,Ud) has a Uniform([0,1]d) distribution, that mY=(Y1,ldots,Yd) has the distribution G on RR+d, and let mX=(X1,ldots,Xd)=(U1Y1,ldots,UdYd). The resulting class of distributions of mX (as G varies over all distributions on RR+d) is called the {sl Scale Mixture of Uniforms} class of distributions, and the corresponding class of densities on RR+d is denoted by calFSMU(d). We study maximum likelihood estimation in the family calFSMU(d). We prove existence of the MLE, establish Fenchel characterizations, and prove strong consistency of the almost surely unique maximum likelihood estimator (MLE) in calFSMU(d). We also provide an asymptotic minimax lower bound for estimating the functional fmapstof(mx) under reasonable differentiability assumptions on fincalFSMU(d) in a neighborhood of mx. We conclude the paper with discussion, conjectures and open problems pertaining to global and local rates of convergence of the MLE.


Full work available at URL: https://arxiv.org/abs/1005.1352




Recommendations




Cites Work


Cited In (15)





This page was built for publication: Nonparametric estimation of multivariate scale mixtures of uniform densities

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q413749)