Formulae and graphs are presented that allow one to compute the variances of three prototypical distributions over a finite number of categories. The distributions are (1) the maximum variance distribution, (2) the uniform distribution, and (3) a unimodal triangular distribution. The use of the variances of these prototypical distributions to make inferences about distribution shapes is illustrated with several examples.
Get full access to this article
View all access options for this article.
References
1.
1. Shapira, Z.From main effects to parameter estimation: Some problems of testing theories of individual choice behavior using aggregated data. Unpublished paper, Carnegie-Mellon University, July, 1979.
2.
2. Messick, D. M. and Sentis, K. P.Tests of an hypothesis of social preferences with attention to the difference between using group means and individual data. Unpublished paper, University of California, Santa Barbara, 1980.
3.
Estes, W. K.The problem of inference from curves based on group data . Psychological Bulletin, 1956, 53, 134-140.
4.
Hook, J. G. and Cook, T. D.Equity theory and the cognitive ability of children. Psychological Bulletin, 1979, 86, 429-445.
5.
Leventhal, G. S. and Anderson, D.Self-interest and the maintenance of equity. Journal of Personality and Social Psychology, 1970, 15, 57-62.
6.
Luce, R. D.Individual Choice Behavior. New York: Wiley, 1959.
7.
Wortman, C. B.Some determinants of perceived control . Journal of Personality and Social Psychology, 1975, 31, 282-294.
