Go to  Advanced Search

Smoothing locally regular processes by Bayesian nonparametric methods, with applications to acid rain data analysis

Show full item record

Files in this item

Files Size Format Description   View
UBC_1986_A6_7 M32.pdf 3.890Mb Adobe Portable Document Format   View/Open
 
Title: Smoothing locally regular processes by Bayesian nonparametric methods, with applications to acid rain data analysis
Author: Ma, Hon Wai
Degree: Master of Science - MSc
Program: Statistics
Copyright Date: 1986
Issue Date: 2010-06-27
Publisher University of British Columbia
Series/Report no. UBC Retrospective Theses Digitization Project [http://www.library.ubc.ca/archives/retro_theses/]
Abstract: We consider the problem of recovering an unknown smooth function from the data using the Bayesian nonparametric approach proposed by Weerahandi and Zidek (1985). Selected nonparametric smoothing methods are reviewed and compared with this new method. At each value of the independent variable, the smooth function is assumed to be expandable in a Taylor series to the pth order. Two methods, cross-validation and "backfitting" are used to estimate the a priori unspecified hyperparameters. Moreover, a data-based procedure is introduced to select the appropriate order p. Finally, an analysis of an acid-rain, wet-deposition time series is included to indicate the efficacy of the proposed methods.
Affiliation: Science, Faculty of
URI: http://hdl.handle.net/2429/26004
Scholarly Level: Graduate

This item appears in the following Collection(s)

Show full item record

UBC Library
1961 East Mall
Vancouver, B.C.
Canada V6T 1Z1
Tel: 604-822-6375
Fax: 604-822-3893