Abstract
We consider the problem of how to measure a “correlation” (or interdependence) between two survey-questionnaire questions. In the real-life questionnaires it is usual to offer several options-answers for most of the questions. Some (or many) questions give the possibility to choose more than one answer. There are very few statistical methods that enable inferences for the questions with multiple answers. We consider two statistics of the chi-square type that serve to confirm a dependence of two questions. As a theoretical basis a notion of “independence” between two multiple questions should be introduced. We propose two definitions (or actually types of definitions): “random” and “generalized Poisson” independences. A simulation study was performed, which is based on those notions. The study confirms applicability of the chi-square statistics, which are similar to the classical ones.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Agresti A. “Categorical Data Analysis”, Wiley, 1990.
Agresti A. Random effects modeling of multiple binary responses using the multivariate binomial logit-normal distribution, Biometrics (2000)
Agresti A. “An Introduction to Categorical Data Analysis”, New York: J. Wiley 1996.
Agresti A., Liu L-M, “Modelling a categorical variable allowing arbitrary many category choices”, Biometrics 55, 936 - 943, 1999.
Andersen E. B., „The statistical analysis of categorical data", Springer Verlag, 1990.
Brier S. S., "Analysis of contingency tables under cluster sampling", Biometrika, 67, pp. 591 - 596, 1980.
Decady Y.J., Thomas D.R., "A simple test of association for contingency tables with multiple column responses", Biometrics 56, pp.893-896, 2000. 220
Fienberg S. E., „The analysis of cross-clssified categorical data", MIT Press, 1978.
Haight F. A. A., "Handbook of the Poisson distribution", J. Wiley, 1967.
Lloyd Ch. J. J., "Statistical analysis of categorical data", J. Wiley, 1999.
Loughin T., Scherer P. N., Testing association in contingency with multiple column responses, Biometrics 54, 630 - 637, 1998.
Matuszewski A., „Consecuencias estadisticas de analisis de tres variables dentro de formalismo de Dempster-Shafer“, Memorias del XIII Foro Nacional de Estadistica, Culiacan (Mexico ), 1996.
Matuszewski A., „Characterization of dependendence between two multivalued variables through the Rasch model - application to construction data-mining algorithms for survey data”, Intelligent Information Systems VII, Proceedings of the Workshop held in Malbork, pp. 128-131, 1998.
Matuszewski A., “Rasch model and correlation for discrete variables”, Proceedings of Intelligent Information Systems VIII, Ustron, pp. 322 - 326, 1999.
Matuszewski A., “Chi-square type statistics for correlation assessment of two multiresponse survey questions”, Proceedings of "Intelligent Information Systems IX", Bystra, pp. 83 - 89, 2000.
Matuszewski A., Bali G., „Un modelo de interdependencia entre respuestas multiples aplicado a la natacion de alto rendimiento“, Memorias del XIII Foro Nacional de Estadistica, Monterrey N.L., pp. 103 - 108, 1998.
Ord J. K., “Families of frequency distributions”, Ch. Griffin, London, 1972
Rao J. N. K., Scott A.J., “On chi-squared tests for multi-way tables with cell proportions estimated from survey data”, Annals of Statistics 12, 46 - 60, 1984.
Thall P. F., “Score tests in the two-way layout of counts”, Commun. Statist. Theory Meth., 21, pp. 3017 - 3036, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Matuszewski, A., Trojanowski, K. (2001). Models of Multiple Response Independence. In: Kłopotek, M.A., Michalewicz, M., Wierzchoń, S.T. (eds) Intelligent Information Systems 2001. Advances in Intelligent and Soft Computing, vol 10. Physica, Heidelberg. https://doi.org/10.1007/978-3-7908-1813-0_18
Download citation
DOI: https://doi.org/10.1007/978-3-7908-1813-0_18
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-7908-1407-1
Online ISBN: 978-3-7908-1813-0
eBook Packages: Springer Book Archive