Modelling dependencies in paired comparison data

Dittrich, Regina; Hatzinger, Reinhold; Katzenbeisser, Walter

doi:10.1016/s0167-9473(01)00106-2

Cited by 22 publications

(20 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in the analysis of preference data it is natural to assume that preferences expressed by the same person in different comparisons involving common objects are dependent (Thurstone, 1927;Dittrich et al, 2002;Böckenholt and Tsai, 2007). When normality is assumed and the objects compared are more than four, different methods have been applied to overcome the computational difficulties of maximum likelihood estimation (Mosteller, 1951;Böckenholt and Tsai, 2001;Train, 2009).…”

Section: Discussionmentioning

confidence: 99%

Hybrid Pairwise Likelihood Analysis of Animal Behavior Experiments

Cattelan

Varin

2013

Biometrics

View full text Add to dashboard Cite

The study of the determinants of contests between animals is an important issue in understanding animal behavior. Tournament experiments among a set of animals are used by zoologists for this purpose. From a statistical point of view, the results of these tournament experiments are naturally analyzed by paired comparison models such as the Bradley-Terry and the Thurstone models. A major complication is the presence of dependence between the outcomes of couples of contests with an animal in common. Likelihood analysis of this type of animal behavior experiments in presence of interdependence between contests is computationally demanding. An alternative fitting method that mixes optimal estimation equations and pairwise likelihood inference is then suggested. The performance of the proposed methodology is investigated by simulation studies and then applied to a real data set about adult male Cape Dwarf Chameleons.

show abstract

Section: Discussionmentioning

confidence: 99%

Hybrid Pairwise Likelihood Analysis of Animal Behavior Experiments

Cattelan

Varin

2013

Biometrics

View full text Add to dashboard Cite

show abstract

“…The pattern models can also be formulated as loglinear models (Dittrich, Hatzinger, and Katzenbeisser 2002). The expected numbers for a whole sequence of preferences y is given as m(y) = m(y 12 , .…”

Section: The Paired Comparison Pattern Modelmentioning

confidence: 99%

“…Derived patterns Dittrich et al 2002). Table 3 shows all possible (full) rankings for J = 3 objects, derived PC patterns and the design structure for a ranking pattern model.…”

Section: Ranksmentioning

confidence: 99%

prefmod: AnRPackage for Modeling Preferences Based on Paired Comparisons, Rankings, or Ratings

Hatzinger¹,

Dittrich²

2012

J. Stat. Soft.

View full text Add to dashboard Cite

The first part of this paper describes a series of loglinear preference models based on paired comparisons, a method of measurement whose aim is to order a set of objects according to an attribute of interest by asking subjects to compare pairs of objects. Based on the basic Bradley-Terry specification, two types of models, the loglinear Bradley-Terry model and a pattern approach are presented. Both methods are extended to include subject and object-specific covariates and some further structural effects. In addition, models for derived paired comparisons (based on rankings and ratings) are also included. Latent classes and missing values can be included. The second part of the paper describes the package prefmod that implements the above models in R. Illustrational applications are provided in the last part of the paper.

show abstract

“…certain two-way interactions between PC-responses, where i represents the common item (cf. Dittrich et al, 2002).…”

Section: Incorporating Dependenciesmentioning

confidence: 99%

A paired comparison approach for the analysis of sets of Likert-scale responses

Dittrich

Francis

Hatzinger

et al. 2007

Statistical Modelling

View full text Add to dashboard Cite

Summary. This paper provides an alternative methodology for the analysis of a set of Likert responses measured on a common attitudinal scale when the primary focus of interest is on the relative importance of items in the set. The method makes fewer assumptions about the distribution of the responses than the more usual approaches such as comparisons of means, MANOVA or ordinal data methods. The approach transforms the Likert responses into paired comparison responses between the items. The complete multivariate pattern of responses thus produced can be analysed by an appropriately reformulated paired comparison model. The dependency structure between item responses can also be modelled flexibly. The advantage of this approach is that sets of Likert responses can be analysed simultaneously within the Generalized Linear Model framework, providing standard likelihood based inference for model selection. This method is applied to a recent international survey on the importance of environmental problems.

show abstract

Modelling dependencies in paired comparison data

Cited by 22 publications

References 16 publications

Hybrid Pairwise Likelihood Analysis of Animal Behavior Experiments

Hybrid Pairwise Likelihood Analysis of Animal Behavior Experiments

prefmod: AnRPackage for Modeling Preferences Based on Paired Comparisons, Rankings, or Ratings

A paired comparison approach for the analysis of sets of Likert-scale responses

Contact Info

Product

Resources

About