Home > Research > Publications & Outputs > Modelling dependency in multivariate paired com...

Research

Electronic data

Links

Text available via DOI:

Keywords

View graph of relations

Modelling dependency in multivariate paired comparisons: a log-linear approach.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Modelling dependency in multivariate paired comparisons: a log-linear approach. / Dittrich, Regina; Francis, Brian; Hatzinger, Reinhold et al.
In: Mathematical Social Sciences, Vol. 52, No. 2, 09.2006, p. 197-209.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Dittrich, R, Francis, B, Hatzinger, R & Katzenbeisser, W 2006, 'Modelling dependency in multivariate paired comparisons: a log-linear approach.', Mathematical Social Sciences, vol. 52, no. 2, pp. 197-209. https://doi.org/10.1016/j.mathsocsci.2006.06.001

APA

Dittrich, R., Francis, B., Hatzinger, R., & Katzenbeisser, W. (2006). Modelling dependency in multivariate paired comparisons: a log-linear approach. Mathematical Social Sciences, 52(2), 197-209. https://doi.org/10.1016/j.mathsocsci.2006.06.001

Vancouver

Dittrich R, Francis B, Hatzinger R, Katzenbeisser W. Modelling dependency in multivariate paired comparisons: a log-linear approach. Mathematical Social Sciences. 2006 Sept;52(2):197-209. doi: 10.1016/j.mathsocsci.2006.06.001

Author

Dittrich, Regina ; Francis, Brian ; Hatzinger, Reinhold et al. / Modelling dependency in multivariate paired comparisons : a log-linear approach. In: Mathematical Social Sciences. 2006 ; Vol. 52, No. 2. pp. 197-209.

Bibtex

@article{281da0663e0f4a34b7405fd71f9c1f19,
title = "Modelling dependency in multivariate paired comparisons: a log-linear approach.",
abstract = "A log-linear representation of the Bradley-Terry model is presented for multivariate paired comparison data, where judges are asked to compare pairs of objects on more than one attribute. By converting such data to multiple binomial responses, dependencies between the decisions of the judges as well as possible association structures between the attributes can be incorporated in the model, providing an advantage over parallel univariate analyses of individual attributes. The approach outlined gives parameters which can be interpreted as (conditional) log–odds and log–odds ratios. As the model is a generalised linear model, parameter estimation can use standard software and the GLM framework can be used to test hypotheses on these parameters.",
keywords = "Paired comparisons, Multivariate Bradley-Terry model , Within-subject dependencies, Multivariate binomial data, Log-linear model , Generalized linear models, GLIM",
author = "Regina Dittrich and Brian Francis and Reinhold Hatzinger and Walter Katzenbeisser",
note = "The final, definitive version of this article has been published in the Journal, Mathematical Social Sciences 52 (2), 2006, {\textcopyright} ELSEVIER.",
year = "2006",
month = sep,
doi = "10.1016/j.mathsocsci.2006.06.001",
language = "English",
volume = "52",
pages = "197--209",
journal = "Mathematical Social Sciences",
issn = "0165-4896",
publisher = "Elsevier",
number = "2",

}

RIS

TY - JOUR

T1 - Modelling dependency in multivariate paired comparisons

T2 - a log-linear approach.

AU - Dittrich, Regina

AU - Francis, Brian

AU - Hatzinger, Reinhold

AU - Katzenbeisser, Walter

N1 - The final, definitive version of this article has been published in the Journal, Mathematical Social Sciences 52 (2), 2006, © ELSEVIER.

PY - 2006/9

Y1 - 2006/9

N2 - A log-linear representation of the Bradley-Terry model is presented for multivariate paired comparison data, where judges are asked to compare pairs of objects on more than one attribute. By converting such data to multiple binomial responses, dependencies between the decisions of the judges as well as possible association structures between the attributes can be incorporated in the model, providing an advantage over parallel univariate analyses of individual attributes. The approach outlined gives parameters which can be interpreted as (conditional) log–odds and log–odds ratios. As the model is a generalised linear model, parameter estimation can use standard software and the GLM framework can be used to test hypotheses on these parameters.

AB - A log-linear representation of the Bradley-Terry model is presented for multivariate paired comparison data, where judges are asked to compare pairs of objects on more than one attribute. By converting such data to multiple binomial responses, dependencies between the decisions of the judges as well as possible association structures between the attributes can be incorporated in the model, providing an advantage over parallel univariate analyses of individual attributes. The approach outlined gives parameters which can be interpreted as (conditional) log–odds and log–odds ratios. As the model is a generalised linear model, parameter estimation can use standard software and the GLM framework can be used to test hypotheses on these parameters.

KW - Paired comparisons

KW - Multivariate Bradley-Terry model

KW - Within-subject dependencies

KW - Multivariate binomial data

KW - Log-linear model

KW - Generalized linear models

KW - GLIM

U2 - 10.1016/j.mathsocsci.2006.06.001

DO - 10.1016/j.mathsocsci.2006.06.001

M3 - Journal article

VL - 52

SP - 197

EP - 209

JO - Mathematical Social Sciences

JF - Mathematical Social Sciences

SN - 0165-4896

IS - 2

ER -