The practical use of semiparametric models in field trials

Maria Durban, Christine A. Hackett, James W. McNicol, Adrian C. Newton, W. T B Thomas, Iain D. Currie

Research output: Contribution to journalArticle

Abstract

This article examines the practical use of semiparametric models in the analysis of field trials-that is, models with parameterized treatment effects and additive terms derived by a data-driven approach using a locally weighted running line smoother (loess). We discuss graphical methods to identify spatial structure in the data and model selection procedures to choose the degree of smoothing. Once the spatial part of the model has been chosen, hypotheses about the treatment effects may be tested. Semiparametric models are used to analyze two barley field trials exhibiting spatial trends. The first has a single experimental treatment and a row-column design. The second has a split-plot design, and we use a semiparametric model which accounts for the randomization at the different strata of this design. We compare the semiparametric analyses with classical analyses of variance and with alternative spatial models. We find that semiparametric models give a good insight into spatial variation in the field and can improve the precision of parameter estimates. ©2003 American Statistical Association and the International Biometric Society.

Original languageEnglish
Pages (from-to)48-66
Number of pages19
JournalJournal of Agricultural, Biological, and Environmental Statistics
Volume8
Issue number1
DOIs
Publication statusPublished - Mar 2003

Fingerprint

graphical method
trial
biometry
smoothing
barley
loess
spatial variation
effect
analysis
parameter
trend

Keywords

  • Bootstrap F test
  • Loess
  • Model selection
  • Smoothing
  • Spatial analysis
  • Split-plot

Cite this

Durban, M., Hackett, C. A., McNicol, J. W., Newton, A. C., Thomas, W. T. B., & Currie, I. D. (2003). The practical use of semiparametric models in field trials. Journal of Agricultural, Biological, and Environmental Statistics, 8(1), 48-66. https://doi.org/10.1198/1085711031265
Durban, Maria ; Hackett, Christine A. ; McNicol, James W. ; Newton, Adrian C. ; Thomas, W. T B ; Currie, Iain D. / The practical use of semiparametric models in field trials. In: Journal of Agricultural, Biological, and Environmental Statistics. 2003 ; Vol. 8, No. 1. pp. 48-66.
@article{372618ac74a4446696c5b7f558579f3e,
title = "The practical use of semiparametric models in field trials",
abstract = "This article examines the practical use of semiparametric models in the analysis of field trials-that is, models with parameterized treatment effects and additive terms derived by a data-driven approach using a locally weighted running line smoother (loess). We discuss graphical methods to identify spatial structure in the data and model selection procedures to choose the degree of smoothing. Once the spatial part of the model has been chosen, hypotheses about the treatment effects may be tested. Semiparametric models are used to analyze two barley field trials exhibiting spatial trends. The first has a single experimental treatment and a row-column design. The second has a split-plot design, and we use a semiparametric model which accounts for the randomization at the different strata of this design. We compare the semiparametric analyses with classical analyses of variance and with alternative spatial models. We find that semiparametric models give a good insight into spatial variation in the field and can improve the precision of parameter estimates. {\circledC}2003 American Statistical Association and the International Biometric Society.",
keywords = "Bootstrap F test, Loess, Model selection, Smoothing, Spatial analysis, Split-plot",
author = "Maria Durban and Hackett, {Christine A.} and McNicol, {James W.} and Newton, {Adrian C.} and Thomas, {W. T B} and Currie, {Iain D.}",
year = "2003",
month = "3",
doi = "10.1198/1085711031265",
language = "English",
volume = "8",
pages = "48--66",
journal = "Journal of Agricultural, Biological, and Environmental Statistics",
issn = "1085-7117",
publisher = "Springer",
number = "1",

}

Durban, M, Hackett, CA, McNicol, JW, Newton, AC, Thomas, WTB & Currie, ID 2003, 'The practical use of semiparametric models in field trials', Journal of Agricultural, Biological, and Environmental Statistics, vol. 8, no. 1, pp. 48-66. https://doi.org/10.1198/1085711031265

The practical use of semiparametric models in field trials. / Durban, Maria; Hackett, Christine A.; McNicol, James W.; Newton, Adrian C.; Thomas, W. T B; Currie, Iain D.

In: Journal of Agricultural, Biological, and Environmental Statistics, Vol. 8, No. 1, 03.2003, p. 48-66.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The practical use of semiparametric models in field trials

AU - Durban, Maria

AU - Hackett, Christine A.

AU - McNicol, James W.

AU - Newton, Adrian C.

AU - Thomas, W. T B

AU - Currie, Iain D.

PY - 2003/3

Y1 - 2003/3

N2 - This article examines the practical use of semiparametric models in the analysis of field trials-that is, models with parameterized treatment effects and additive terms derived by a data-driven approach using a locally weighted running line smoother (loess). We discuss graphical methods to identify spatial structure in the data and model selection procedures to choose the degree of smoothing. Once the spatial part of the model has been chosen, hypotheses about the treatment effects may be tested. Semiparametric models are used to analyze two barley field trials exhibiting spatial trends. The first has a single experimental treatment and a row-column design. The second has a split-plot design, and we use a semiparametric model which accounts for the randomization at the different strata of this design. We compare the semiparametric analyses with classical analyses of variance and with alternative spatial models. We find that semiparametric models give a good insight into spatial variation in the field and can improve the precision of parameter estimates. ©2003 American Statistical Association and the International Biometric Society.

AB - This article examines the practical use of semiparametric models in the analysis of field trials-that is, models with parameterized treatment effects and additive terms derived by a data-driven approach using a locally weighted running line smoother (loess). We discuss graphical methods to identify spatial structure in the data and model selection procedures to choose the degree of smoothing. Once the spatial part of the model has been chosen, hypotheses about the treatment effects may be tested. Semiparametric models are used to analyze two barley field trials exhibiting spatial trends. The first has a single experimental treatment and a row-column design. The second has a split-plot design, and we use a semiparametric model which accounts for the randomization at the different strata of this design. We compare the semiparametric analyses with classical analyses of variance and with alternative spatial models. We find that semiparametric models give a good insight into spatial variation in the field and can improve the precision of parameter estimates. ©2003 American Statistical Association and the International Biometric Society.

KW - Bootstrap F test

KW - Loess

KW - Model selection

KW - Smoothing

KW - Spatial analysis

KW - Split-plot

UR - http://www.scopus.com/inward/record.url?scp=5444272243&partnerID=8YFLogxK

U2 - 10.1198/1085711031265

DO - 10.1198/1085711031265

M3 - Article

VL - 8

SP - 48

EP - 66

JO - Journal of Agricultural, Biological, and Environmental Statistics

JF - Journal of Agricultural, Biological, and Environmental Statistics

SN - 1085-7117

IS - 1

ER -