A Bayesian Approach to Prediction and Variable Selection Using Nonstationary Gaussian Processes

A Bayesian Approach to Prediction and Variable Selection Using Nonstationary Gaussian Processes

Bibliographic Details
Main Author: Davis, Casey Benjamin
Language:English
Published: The Ohio State University / OhioLINK 2015
Subjects:
Statistics
nonstationary
Gaussian processes
Bayesian
prediction
variable selection
screening
Online Access:http://rave.ohiolink.edu/etdc/view?acc_num=osu1429712146
id ndltd-OhioLink-oai-etd.ohiolink.edu-osu1429712146
record_format oai_dc
spelling ndltd-OhioLink-oai-etd.ohiolink.edu-osu14297121462021-08-03T06:30:31Z A Bayesian Approach to Prediction and Variable Selection Using Nonstationary Gaussian Processes Davis, Casey Benjamin Statistics nonstationary Gaussian processes Bayesian prediction variable selection screening This research proposes a Bayesian formulation of the Composite Gaussian Process(GP) of Ba and Joseph (2012). The composite Gaussian Process model generalizes theregression plus stationary GP model in both a stationary and nonstationary manner.The likelihood stage of the model combines two independent Gaussian processes andthe remaining stages put priors on the means, variances, and correlation parametersof the Gaussian processes. Markov chain Monte Carlo methods are used to estimateposterior predictions and prediction intervals and are compared with predictions fromthe composite GP model, a treed GP model, and a universal kriging approach. Thisresearch also develops screening methodology for experiments with many inputs thatis based on a hierarchical Bayesian Gaussian process model. This flexible model is able to describe output functions having varying range and patterns of fluctuation. Screening is accomplished by identifying inputs with small posterior probability ofbeing correlated with the output by incorporating a Bayesian "variable selection"prior for the correlation parameters. 2015-05-28 English text The Ohio State University / OhioLINK http://rave.ohiolink.edu/etdc/view?acc_num=osu1429712146 http://rave.ohiolink.edu/etdc/view?acc_num=osu1429712146 unrestricted This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws.
collection NDLTD
language English
sources NDLTD
topic Statistics
nonstationary
Gaussian processes
Bayesian
prediction
variable selection
screening
spellingShingle Statistics
nonstationary
Gaussian processes
Bayesian
prediction
variable selection
screening
Davis, Casey Benjamin
A Bayesian Approach to Prediction and Variable Selection Using Nonstationary Gaussian Processes
author Davis, Casey Benjamin
author_facet Davis, Casey Benjamin
author_sort Davis, Casey Benjamin
title A Bayesian Approach to Prediction and Variable Selection Using Nonstationary Gaussian Processes
title_short A Bayesian Approach to Prediction and Variable Selection Using Nonstationary Gaussian Processes
title_full A Bayesian Approach to Prediction and Variable Selection Using Nonstationary Gaussian Processes
title_fullStr A Bayesian Approach to Prediction and Variable Selection Using Nonstationary Gaussian Processes
title_full_unstemmed A Bayesian Approach to Prediction and Variable Selection Using Nonstationary Gaussian Processes
title_sort bayesian approach to prediction and variable selection using nonstationary gaussian processes
publisher The Ohio State University / OhioLINK
publishDate 2015
url http://rave.ohiolink.edu/etdc/view?acc_num=osu1429712146
work_keys_str_mv AT daviscaseybenjamin abayesianapproachtopredictionandvariableselectionusingnonstationarygaussianprocesses
AT daviscaseybenjamin bayesianapproachtopredictionandvariableselectionusingnonstationarygaussianprocesses
_version_ 1719438134328950784

Similar Items