A generalization of the Eisler-Ekman similarity function is presented which fits data at least as well as some of the other similarity functions that have been proposed. While these functions either are parameterless or merely contain correcting parameters added to improve goodness of fit, the general similarity function has two parameters that are inherent to the model of similarity which the function represents.
Get full access to this article
View all access options for this article.
References
1.
EislerH.A general differential equation in psychophysics: Derivation and empirical test. Scand. J. Psychol., 1963, 4, 265–272.
2.
EislerH.EkmanG.A mechanism of subjective similarity. Acta Psychol., 1959, 16, 1–10.
3.
EislerH.RoskamE. E.Multidimensional similarity: An experimental and theoretical comparison of vector, distance, and set theoretical models: I. Models and internal consistency of data. Acta Psychol., 1977, 41, 1–46.
4.
EkmanG.EngenT.KuennapasT.LindmanR.A quantitative principle of qualitative similarity. J. exp. Psychol., 1964, 68, 530–536.
5.
GregsonR. A. M.Psychometrics of similarity.New York: Academic Press, 1975.
6.
KuennapasT.Visual perception of capital letters; multidimensional ratio scaling and multidimensional similarity. Scand. J. Psychol., 1966, 7, 189–196.
7.
SjobergL.Models of similarity and intensity. Psychol. Bull., 1975, 82, 191–206.
