Evaluating acceptance of cashew juice flavor via mixed proportional odds model

Authors

  • Laura V. T. de Paula
  • Ana Maria S. de Araújo
  • Idemauro Antonio R. de Lara
  • Tatiana O. Lemos

Keywords:

Proportional odds models, Mixed models, Ordinal package, Cashew juice

Abstract

The proportional odds model is a method that can be used to describe the relationship between ordinal categorical variables and one or more covariates. It is an extension of generalized linear models, it allows to obtain cumulative probabilities for each response category and, consequently, and marginal probabilities. This paper aims to fit a proportional odds model to verify acceptance of flavored cashew juice. The experiment was conducted in Fortaleza-CE, where one 100 (hundred) untrained tasters, pre viously selected, after proving a small amount of juice were asked to answer several questions, among them: “Please use the scale below, describe how much you liked or disliked of each sample’s flavor”. The answer to this question consists of several ordinal categories for five different brands of cashew juice. A model was adjusted for this experiment, and in order to deal with possible dependencies among observations, a random effect was added to the proportional odds model, turning into a mixed model. Data analysis and the fit of the models were made with the aid of ordinal package available in R soft ware, version 2.15. 

References

CHRISTENSEN, R.H. Analysis of ordinal data with cumulative link models estimation with the R-package ordinal. Disponível em: http://cran.r-project.org/web/packages/ordinal/vignettes/clm_intro.pdf. Acesso em: 10 abril 2013.

CHRISTENSEN, R.H. Analysis of sensory ratings data with cumulative link models. Journal de la Societé Française de Statistique. (Submetido)

COSTA, T. R. Modelos lineares mistos: uma aplicação na produção de leite de vacas da raça sindi. 2010. 79 p. Dissertação (Mestrado em Biometria e Estatística Aplicada) - Universidade Federal Rural de Pernambuco, UFRPE, Recife, 2010.

MACFIE, H. J.; BRATCHELL, N.; GREENHOFF, K.; VALLIS, L. Designs to balance the effect of order of presentation and first-order carry-over effects in hall tests. Journal of Sensory Studies v. 4, n. 2, p. 129 148, 1989.

McCULLAGH, P. Regression Methods for Ordinal Data. Journal of The Royal Statistical Society, Series B, London, v. 42, p. 109 142, 1980.

STRAM, D.O.; WEI, L.J.; WARE, J.H. Analysis of repeated ordered categorical outcomes with possibly missing observations and time-dependent covariates. Journal of American Statistical Association, Boston, v. 83, p. 631 637, 1988.

R CORE TEAM. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. 2012. Disponível em: http://www.R-project.org/. Acesso em: 10 abril 2013.

Published

27-10-2014

How to Cite

de Paula, L. V. T., de Araújo, A. M. S., de Lara, I. A. R., & Lemos, T. O. (2014). Evaluating acceptance of cashew juice flavor via mixed proportional odds model. Sigmae, 2(3), 65–70. Retrieved from https://publicacoes.unifal-mg.edu.br/revistas/index.php/sigmae/article/view/318