A non-gaussian spatial process model for opacity of flocculated paper

Patrick E. Brown, Peter J. Diggle, Robin Henderson

Research output: Contribution to journalArticle

Abstract

Product quality in the paper-making industry can be assessed by opacity of a linear trace through continuous production sheets, summarized in spectral form. We adopt a class of non-Gaussian stochastic models for continuous spatial variation to describe data of this type. The model has flexible covariance structure, physically interpretable parameters and allows several scales of variation for the underlying process. We derive the spectral properties of the model, and develop methods of parameter estimation based on maximum likelihood in the frequency domain. The methods are illustrated using sample data from a UK mill.

Original languageEnglish (US)
Pages (from-to)355-368
Number of pages14
JournalScandinavian Journal of Statistics
Volume30
Issue number2
StatePublished - Jun 2003
Externally publishedYes

Fingerprint

Opacity
Spatial Process
Spatial Model
Process Model
Flexible Structure
Covariance Structure
Spectral Properties
Maximum Likelihood
Frequency Domain
Stochastic Model
Parameter Estimation
Trace
Industry
Model
Process model
Form
Class
Spatial variation
Maximum likelihood
Parameter estimation

Keywords

  • Matérn functions
  • Paper formation
  • Poisson cluster process
  • Spectral analysis

ASJC Scopus subject areas

  • Mathematics(all)
  • Statistics and Probability

Cite this

Brown, P. E., Diggle, P. J., & Henderson, R. (2003). A non-gaussian spatial process model for opacity of flocculated paper. Scandinavian Journal of Statistics, 30(2), 355-368.

A non-gaussian spatial process model for opacity of flocculated paper. / Brown, Patrick E.; Diggle, Peter J.; Henderson, Robin.

In: Scandinavian Journal of Statistics, Vol. 30, No. 2, 06.2003, p. 355-368.

Research output: Contribution to journalArticle

Brown, PE, Diggle, PJ & Henderson, R 2003, 'A non-gaussian spatial process model for opacity of flocculated paper', Scandinavian Journal of Statistics, vol. 30, no. 2, pp. 355-368.
Brown, Patrick E. ; Diggle, Peter J. ; Henderson, Robin. / A non-gaussian spatial process model for opacity of flocculated paper. In: Scandinavian Journal of Statistics. 2003 ; Vol. 30, No. 2. pp. 355-368.
@article{8725b04f4c0c419097670c2f69d8dc62,
title = "A non-gaussian spatial process model for opacity of flocculated paper",
abstract = "Product quality in the paper-making industry can be assessed by opacity of a linear trace through continuous production sheets, summarized in spectral form. We adopt a class of non-Gaussian stochastic models for continuous spatial variation to describe data of this type. The model has flexible covariance structure, physically interpretable parameters and allows several scales of variation for the underlying process. We derive the spectral properties of the model, and develop methods of parameter estimation based on maximum likelihood in the frequency domain. The methods are illustrated using sample data from a UK mill.",
keywords = "Mat{\'e}rn functions, Paper formation, Poisson cluster process, Spectral analysis",
author = "Brown, {Patrick E.} and Diggle, {Peter J.} and Robin Henderson",
year = "2003",
month = "6",
language = "English (US)",
volume = "30",
pages = "355--368",
journal = "Scandinavian Journal of Statistics",
issn = "0303-6898",
publisher = "Wiley-Blackwell",
number = "2",

}

TY - JOUR

T1 - A non-gaussian spatial process model for opacity of flocculated paper

AU - Brown, Patrick E.

AU - Diggle, Peter J.

AU - Henderson, Robin

PY - 2003/6

Y1 - 2003/6

N2 - Product quality in the paper-making industry can be assessed by opacity of a linear trace through continuous production sheets, summarized in spectral form. We adopt a class of non-Gaussian stochastic models for continuous spatial variation to describe data of this type. The model has flexible covariance structure, physically interpretable parameters and allows several scales of variation for the underlying process. We derive the spectral properties of the model, and develop methods of parameter estimation based on maximum likelihood in the frequency domain. The methods are illustrated using sample data from a UK mill.

AB - Product quality in the paper-making industry can be assessed by opacity of a linear trace through continuous production sheets, summarized in spectral form. We adopt a class of non-Gaussian stochastic models for continuous spatial variation to describe data of this type. The model has flexible covariance structure, physically interpretable parameters and allows several scales of variation for the underlying process. We derive the spectral properties of the model, and develop methods of parameter estimation based on maximum likelihood in the frequency domain. The methods are illustrated using sample data from a UK mill.

KW - Matérn functions

KW - Paper formation

KW - Poisson cluster process

KW - Spectral analysis

UR - http://www.scopus.com/inward/record.url?scp=0038178120&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038178120&partnerID=8YFLogxK

M3 - Article

VL - 30

SP - 355

EP - 368

JO - Scandinavian Journal of Statistics

JF - Scandinavian Journal of Statistics

SN - 0303-6898

IS - 2

ER -