Title: A multiresolution approach to time warping achieved by a Bayesian prior-posterior transfer fitting strategy
Authors: Slaets, Leen
Claeskens, Gerda
Silverman, Bernard
Issue Date: Jan-2009
Publisher: K.U.Leuven - Faculty of Business and Economics
Series Title: FBE Research Report KBI_0901 pages:1-31
Abstract: The procedure known as warping aims at reducing phase variability in a sample of functional curve observations, by applying a smooth bijection to the argument of each of the functions. We propose a natural representation of warping functions in terms of a new type of elementary function named `warping component functions' which are combined into the warping function by composition. A sequential Bayesian estimation strategy is introduced, which fits a series of models and transfers the posterior of the previous fit into the prior of the next fit. Model selection is based on a warping analogue to wavelet thresholding, combined with Bayesian inference.
Publication status: published
KU Leuven publication type: IR
Appears in Collections:Research Center for Operations Research and Business Statistics (ORSTAT), Leuven

Files in This Item:
File Description Status SizeFormat
KBI_0901.pdfA multiresolution approach to time warping achieved by a bayesian prior-posterior transfer fitting strategy Published 2448KbAdobe PDFView/Open


All items in Lirias are protected by copyright, with all rights reserved.