A note on P-spline additive models with correlated errors

Maria Durbán; Iain D. Currie

A note on P-spline additive models with correlated errors

Maria Durbán, Iain D. Currie

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

Abstract

We consider additive models with k smooth terms and correlated errors, and use the penalised spline approach of Eilers & Marx (1996) to estimate the smooth functions. We obtain explicit expressions for the hat-matrix of the model and each individual curve. P-splines are represented as mixed models and REML is used to select the smoothing and correlation parameters. The method is applied to the analysis of some time series data.

Original language	English
Pages (from-to)	251-262
Number of pages	12
Journal	Computational Statistics
Volume	18
Issue number	2
Publication status	Published - 2003

Keywords

Additive model
Back-fitting
Mixed models
P-spline
REML
Serial correlation

Cite this

@article{1c216bb32813417d88fdb762592dba16,

title = "A note on P-spline additive models with correlated errors",

abstract = "We consider additive models with k smooth terms and correlated errors, and use the penalised spline approach of Eilers & Marx (1996) to estimate the smooth functions. We obtain explicit expressions for the hat-matrix of the model and each individual curve. P-splines are represented as mixed models and REML is used to select the smoothing and correlation parameters. The method is applied to the analysis of some time series data.",

keywords = "Additive model, Back-fitting, Mixed models, P-spline, REML, Serial correlation",

author = "Maria Durb{\'a}n and Currie, {Iain D.}",

year = "2003",

language = "English",

volume = "18",

pages = "251--262",

journal = "Computational Statistics",

issn = "1613-9658",

publisher = "Springer",

number = "2",

}

TY - JOUR

T1 - A note on P-spline additive models with correlated errors

AU - Durbán, Maria

AU - Currie, Iain D.

PY - 2003

Y1 - 2003

N2 - We consider additive models with k smooth terms and correlated errors, and use the penalised spline approach of Eilers & Marx (1996) to estimate the smooth functions. We obtain explicit expressions for the hat-matrix of the model and each individual curve. P-splines are represented as mixed models and REML is used to select the smoothing and correlation parameters. The method is applied to the analysis of some time series data.

AB - We consider additive models with k smooth terms and correlated errors, and use the penalised spline approach of Eilers & Marx (1996) to estimate the smooth functions. We obtain explicit expressions for the hat-matrix of the model and each individual curve. P-splines are represented as mixed models and REML is used to select the smoothing and correlation parameters. The method is applied to the analysis of some time series data.

KW - Additive model

KW - Back-fitting

KW - Mixed models

KW - P-spline

KW - REML

KW - Serial correlation

UR - http://www.scopus.com/inward/record.url?scp=0038807496&partnerID=8YFLogxK

M3 - Article

SN - 1613-9658

VL - 18

SP - 251

EP - 262

JO - Computational Statistics

JF - Computational Statistics

IS - 2

ER -

A note on P-spline additive models with correlated errors

Abstract

Keywords

Other files and links

Fingerprint

Cite this