Correlation coefficients for more than one scale type: An alternative to the Janson and Vegelius approach
- 82 Downloads
Janson and Vegelius have recently suggested a family of correlations for variables of mixed scale types, including nominal scales. The resulting correlations areE-coefficients, which means that they are unity if the variables involved are identical up to permissible transformations, and that they can be considered as inner products in a Euclidian space. Some of the coefficients of the correlation family suggested by Janson and Vegelius are generalized squared product-moment correlations and some are not. In the present paper, a family of correlations for variables of mixed scale types is advocated all members of which are generalized squared product-moment correlations. Some practical advantages of the latter family are explained.
Key wordsmixed levels of measurement association coefficients
Unable to display preview. Download preview PDF.
- Daniels, H. E. (1944). The relation between measures of correlation in the universe of sample permutations.Biometrika, 36, 129–135.Google Scholar
- Gifi, A. (1981).Nonlinear multivariate analysis. University of Leiden, Department of Data Theory.Google Scholar
- Holley, J. W., & Guilford, J. P. (1964). A note on theG-index of agreement.Educational and Psychological Measurement, 24, 749–753.Google Scholar
- Janson, S., & Vegelius, J. (1978a). On the applicability of truncated principal component analysis based on correlation coefficients for nominal scales.Applied Psychological Measurement, 2, 135–145.Google Scholar
- Janson, S., & Vegelius, J. (1978b).Correlation coefficients for more than one scale type and symmetrization as a method of obtaining them (Research Report 78-2). Uppsala: University of Uppsala, Department of Statistics.Google Scholar
- Janson, S., & Vegelius, J. (1982b). TheJ-index as a measure of nominal scale response agreement.Applied Psychological Measurement, 6, 111–121.Google Scholar
- Kendall, M. G. (1955).Rank correlation methods (ed. 2). London: Griffin.Google Scholar
- ten Berge, J. M. F. (in press). Rotation to perfect congruence and the cross-validation of component weights across populations.Multivariate Behavioral Research,21, 41–61, 262–266.Google Scholar
- Tucker, L. R. (1978).A method for synthesis of factor analysis studies (Personnel Research Section Report No. 984). Washington, D. C.: Department of the Army.Google Scholar
- Vegelius, J. (1978). On the utility of theE-correlation coefficient concept in psychological research.Educational and Psychological Measurement, 38, 605–611.Google Scholar