Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/6038
Title: A variational Bayes approach to a semiparametric regression using Gaussian process priors
Authors: Ong, Victor M. H.
Mensah, David K.
Nott, David J.
Keywords: Cosine series
Gaussian process
Model selection
Shape restricted regression
Variational Bayes
Issue Date: 2016
Publisher: University of Cape Coast
Abstract: This paper presents a vibrational Bayes approach to a semi-parametric regression model that consists of parametric and nonparametric components. The assumed univariate nonparametric component is represented with a cosine series based on a spectral analysis of Gaussian process priors. Here, we develop fast variational methods for fitting the semi parametric regression model that reduce the computation time by an order of magnitude over Markov chain Monte Carlo methods. Further, we explore the possible use of the variational lower bound and variational information criteria for model choice of a parametric regression model against a semi parametric alternative. In addition, variational methods are developed for estimating univariate shape-restricted regression functions that are monotonic, monotonic convex or monotonic concave. Since these variational methods are approximate, we explore some of the trade-ofs involved in using them in terms of speed, accuracy and automation of the implementation in comparison with Markov chain Monte Carlo methods and discuss their potential and limitations
Description: 39p:, ill.
URI: http://hdl.handle.net/123456789/6038
ISSN: 23105496
Appears in Collections:Department of Mathematics & Statistics

Files in This Item:
File Description SizeFormat 
A variational Bayes approach to a.pdfArticle772.78 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.