Shape-restricted nonparametric regression with overall noisy measurements

Authors:   Pflug GC, Wets RJ-B

Publication Year:   2013

Reference:  Journal of Nonparametric Statistics, Article in press (Published online 13 February 2013)

Abstract

For a nonparametric regression problem with errors in variables, we consider a shape-restricted regression function estimate, which does not require the choice of bandwidth parameters. We demonstrate that this estimate is consistent for classes of regression function candidates, which are closed under the graph topology.
KEYWORDS: Nonparametric regression; Error in variables; Graph topology; Constrained maximum likelihood; Shape restrictions

VIEW CONTENT

DOI: http://dx.doi.org/10.1080/10485252.2012.754890

International Institute for Applied Systems Analysis (IIASA)
Schlossplatz 1, A-2361 Laxenburg, Austria
Phone: (+43 2236) 807 0 Fax:(+43 2236) 71 313

Twitter Facebook Youtube
Follow us on