Gaussian Process Functional Regression Modelling for Batch Data

J.Q. Shi; B. Wang; R. Murray-Smith; D.M. Titterington

doi:10.1111/j.1541-0420.2007.00758.x

Gaussian Process Functional Regression Modelling for Batch Data

J.Q. Shi, B. Wang, R. Murray-Smith, D.M. Titterington

Mathematics

Research output: Contribution to journal › Article › peer-review

Abstract

A Gaussian process functional regression model is proposed for the analysis of batch data. Covariance structure and mean structure are considered simultaneously, with the covariance structure modeled by a Gaussian process regression model and the mean structure modeled by a functional regression model. The model allows the inclusion of covariates in both the covariance structure and the mean structure. It models the nonlinear relationship between a functional output variable and a set of functional and nonfunctional covariates. Several applications and simulation studies are reported and show that the method provides very good results for curve fitting and prediction.

Original language	English
Pages (from-to)	714-723
Number of pages	9
Journal	Biometrics (Journal of the International Biometric Society)
Volume	63
Issue number	3
DOIs	https://doi.org/10.1111/j.1541-0420.2007.00758.x
Publication status	Published - 27 Feb 2007

Keywords

Batch data • B-spline • Functional data analysis • Gaussian process functional regression model • Gaussian process regression model • Multiple-step-ahead forecasting • Nonparametric curve fitting

Access to Document

10.1111/j.1541-0420.2007.00758.x

http://dx.doi.org/10.1111/j.1541-0420.2007.00758.x

Cite this

@article{0132a95ee64a4c8591a424d6c2513561,

title = "Gaussian Process Functional Regression Modelling for Batch Data",

abstract = "A Gaussian process functional regression model is proposed for the analysis of batch data. Covariance structure and mean structure are considered simultaneously, with the covariance structure modeled by a Gaussian process regression model and the mean structure modeled by a functional regression model. The model allows the inclusion of covariates in both the covariance structure and the mean structure. It models the nonlinear relationship between a functional output variable and a set of functional and nonfunctional covariates. Several applications and simulation studies are reported and show that the method provides very good results for curve fitting and prediction.",

keywords = "Batch data • B-spline • Functional data analysis • Gaussian process functional regression model • Gaussian process regression model • Multiple-step-ahead forecasting • Nonparametric curve fitting",

author = "J.Q. Shi and B. Wang and R. Murray-Smith and D.M. Titterington",

year = "2007",

month = feb,

day = "27",

doi = "10.1111/j.1541-0420.2007.00758.x",

language = "English",

volume = "63",

pages = "714--723",

journal = "Biometrics (Journal of the International Biometric Society)",

issn = "1541-0420",

publisher = "Wiley-Blackwell",

number = "3",

}

TY - JOUR

T1 - Gaussian Process Functional Regression Modelling for Batch Data

AU - Shi, J.Q.

AU - Wang, B.

AU - Murray-Smith, R.

AU - Titterington, D.M.

PY - 2007/2/27

Y1 - 2007/2/27

N2 - A Gaussian process functional regression model is proposed for the analysis of batch data. Covariance structure and mean structure are considered simultaneously, with the covariance structure modeled by a Gaussian process regression model and the mean structure modeled by a functional regression model. The model allows the inclusion of covariates in both the covariance structure and the mean structure. It models the nonlinear relationship between a functional output variable and a set of functional and nonfunctional covariates. Several applications and simulation studies are reported and show that the method provides very good results for curve fitting and prediction.

AB - A Gaussian process functional regression model is proposed for the analysis of batch data. Covariance structure and mean structure are considered simultaneously, with the covariance structure modeled by a Gaussian process regression model and the mean structure modeled by a functional regression model. The model allows the inclusion of covariates in both the covariance structure and the mean structure. It models the nonlinear relationship between a functional output variable and a set of functional and nonfunctional covariates. Several applications and simulation studies are reported and show that the method provides very good results for curve fitting and prediction.

KW - Batch data • B-spline • Functional data analysis • Gaussian process functional regression model • Gaussian process regression model • Multiple-step-ahead forecasting • Nonparametric curve fitting

U2 - 10.1111/j.1541-0420.2007.00758.x

DO - 10.1111/j.1541-0420.2007.00758.x

M3 - Article

SN - 1541-0420

VL - 63

SP - 714

EP - 723

JO - Biometrics (Journal of the International Biometric Society)

JF - Biometrics (Journal of the International Biometric Society)

IS - 3

ER -