A composite likelihood approach to computer model calibration with high-dimensional spatial data

Won Chang, Murali Haran, Roman Olson, Klaus Keller

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In this paper, we introduce a composite likelihood-based approach to perform computer model calibration with high-dimensional spatial data. While composite likelihood has been studied extensively in the context of spatial statistics, computer model calibration using composite likelihood poses several new challenges. We propose a computationally efficient approach for Bayesian computer model calibration using composite likelihood. We also develop a methodology based on asymptotic theory for adjusting the composite likelihood posterior distribution so that it accurately represents posterior uncertainties. We study the application of our approach in the context of calibration for a climate model.

Original languageEnglish (US)
Pages (from-to)243-259
Number of pages17
JournalStatistica Sinica
Volume25
Issue number1
DOIs
StatePublished - Jan 2015

Fingerprint

Composite Likelihood
Model Calibration
Computer Model
Spatial Data
High-dimensional Data
Spatial Statistics
Climate Models
Asymptotic Theory
Bayesian Model
Posterior distribution
Calibration
Model calibration
Uncertainty
Methodology

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{587b52edb53741a1996065e2b90e98d8,
title = "A composite likelihood approach to computer model calibration with high-dimensional spatial data",
abstract = "In this paper, we introduce a composite likelihood-based approach to perform computer model calibration with high-dimensional spatial data. While composite likelihood has been studied extensively in the context of spatial statistics, computer model calibration using composite likelihood poses several new challenges. We propose a computationally efficient approach for Bayesian computer model calibration using composite likelihood. We also develop a methodology based on asymptotic theory for adjusting the composite likelihood posterior distribution so that it accurately represents posterior uncertainties. We study the application of our approach in the context of calibration for a climate model.",
author = "Won Chang and Murali Haran and Roman Olson and Klaus Keller",
year = "2015",
month = "1",
doi = "10.5705/ss.2013.219w",
language = "English (US)",
volume = "25",
pages = "243--259",
journal = "Statistica Sinica",
issn = "1017-0405",
publisher = "Institute of Statistical Science",
number = "1",

}

A composite likelihood approach to computer model calibration with high-dimensional spatial data. / Chang, Won; Haran, Murali; Olson, Roman; Keller, Klaus.

In: Statistica Sinica, Vol. 25, No. 1, 01.2015, p. 243-259.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A composite likelihood approach to computer model calibration with high-dimensional spatial data

AU - Chang, Won

AU - Haran, Murali

AU - Olson, Roman

AU - Keller, Klaus

PY - 2015/1

Y1 - 2015/1

N2 - In this paper, we introduce a composite likelihood-based approach to perform computer model calibration with high-dimensional spatial data. While composite likelihood has been studied extensively in the context of spatial statistics, computer model calibration using composite likelihood poses several new challenges. We propose a computationally efficient approach for Bayesian computer model calibration using composite likelihood. We also develop a methodology based on asymptotic theory for adjusting the composite likelihood posterior distribution so that it accurately represents posterior uncertainties. We study the application of our approach in the context of calibration for a climate model.

AB - In this paper, we introduce a composite likelihood-based approach to perform computer model calibration with high-dimensional spatial data. While composite likelihood has been studied extensively in the context of spatial statistics, computer model calibration using composite likelihood poses several new challenges. We propose a computationally efficient approach for Bayesian computer model calibration using composite likelihood. We also develop a methodology based on asymptotic theory for adjusting the composite likelihood posterior distribution so that it accurately represents posterior uncertainties. We study the application of our approach in the context of calibration for a climate model.

UR - http://www.scopus.com/inward/record.url?scp=84959877566&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959877566&partnerID=8YFLogxK

U2 - 10.5705/ss.2013.219w

DO - 10.5705/ss.2013.219w

M3 - Article

AN - SCOPUS:84959877566

VL - 25

SP - 243

EP - 259

JO - Statistica Sinica

JF - Statistica Sinica

SN - 1017-0405

IS - 1

ER -