Bayesian functional data analysis using WinBUGS

Ciprian M Crainiceanu, A. Jeffrey Goldsmith

Research output: Contribution to journalArticle

Abstract

We provide user friendly software for Bayesian analysis of functional data models using WinBUGS 1.4. The excellent properties of Bayesian analysis in this context are due to: (1) dimensionality reduction, which leads to low dimensional projection bases; (2) mixed model representation of functional models, which provides a modular approach to model extension; and (3) orthogonality of the principal component bases, which contributes to excellent chain convergence and mixing properties. Our paper provides one more, essential, reason for using Bayesian analysis for functional models: the existence of software.

Original languageEnglish (US)
Pages (from-to)1-33
Number of pages33
JournalJournal of Statistical Software
Volume32
Issue number11
StatePublished - Jan 2010

Fingerprint

WinBUGS
Functional Data Analysis
Functional Model
Bayesian Analysis
Functional Data
Software
Mixed Model
Dimensionality Reduction
Principal Components
Orthogonality
Data Model
Projection
Data structures
Bayesian analysis
Model

Keywords

  • Covariance
  • MCMC
  • Mixed effects
  • Smoothing

ASJC Scopus subject areas

  • Software
  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Bayesian functional data analysis using WinBUGS. / Crainiceanu, Ciprian M; Goldsmith, A. Jeffrey.

In: Journal of Statistical Software, Vol. 32, No. 11, 01.2010, p. 1-33.

Research output: Contribution to journalArticle

Crainiceanu, Ciprian M ; Goldsmith, A. Jeffrey. / Bayesian functional data analysis using WinBUGS. In: Journal of Statistical Software. 2010 ; Vol. 32, No. 11. pp. 1-33.
@article{25447a26f1fe44529064ff076d672bc0,
title = "Bayesian functional data analysis using WinBUGS",
abstract = "We provide user friendly software for Bayesian analysis of functional data models using WinBUGS 1.4. The excellent properties of Bayesian analysis in this context are due to: (1) dimensionality reduction, which leads to low dimensional projection bases; (2) mixed model representation of functional models, which provides a modular approach to model extension; and (3) orthogonality of the principal component bases, which contributes to excellent chain convergence and mixing properties. Our paper provides one more, essential, reason for using Bayesian analysis for functional models: the existence of software.",
keywords = "Covariance, MCMC, Mixed effects, Smoothing",
author = "Crainiceanu, {Ciprian M} and Goldsmith, {A. Jeffrey}",
year = "2010",
month = "1",
language = "English (US)",
volume = "32",
pages = "1--33",
journal = "Journal of Statistical Software",
issn = "1548-7660",
publisher = "University of California at Los Angeles",
number = "11",

}

TY - JOUR

T1 - Bayesian functional data analysis using WinBUGS

AU - Crainiceanu, Ciprian M

AU - Goldsmith, A. Jeffrey

PY - 2010/1

Y1 - 2010/1

N2 - We provide user friendly software for Bayesian analysis of functional data models using WinBUGS 1.4. The excellent properties of Bayesian analysis in this context are due to: (1) dimensionality reduction, which leads to low dimensional projection bases; (2) mixed model representation of functional models, which provides a modular approach to model extension; and (3) orthogonality of the principal component bases, which contributes to excellent chain convergence and mixing properties. Our paper provides one more, essential, reason for using Bayesian analysis for functional models: the existence of software.

AB - We provide user friendly software for Bayesian analysis of functional data models using WinBUGS 1.4. The excellent properties of Bayesian analysis in this context are due to: (1) dimensionality reduction, which leads to low dimensional projection bases; (2) mixed model representation of functional models, which provides a modular approach to model extension; and (3) orthogonality of the principal component bases, which contributes to excellent chain convergence and mixing properties. Our paper provides one more, essential, reason for using Bayesian analysis for functional models: the existence of software.

KW - Covariance

KW - MCMC

KW - Mixed effects

KW - Smoothing

UR - http://www.scopus.com/inward/record.url?scp=77949334921&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949334921&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:77949334921

VL - 32

SP - 1

EP - 33

JO - Journal of Statistical Software

JF - Journal of Statistical Software

SN - 1548-7660

IS - 11

ER -