Three algorithms for selecting a subset of originally available items to maximize coefficient alpha, including one advanced by Serlin and Kaiser (1976), were compared on the size of the resulting alpha and computation time required with nine sets of data. Results indicated that a combination of the two alternate algorithms proposed would perform better than the Serlin-Kaiser method. The characteristics of a computer program to perform these item analyses are described.
Get full access to this article
View all access options for this article.
References
1.
Crano, W. D. and Brewer, M. B.Principles of research in social psychology. New York: McGraw-Hill, 1973.
2.
Echternacht, G.Reliability and validity of item option weighting schemes. EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 1976, 36, 301-309.
3.
Lord, F. M.Some relations between Guttman's principal components of scale analysis and other psychometric theory. Psychometrika, 1958, 23, 291-296.
4.
Morris, J. D. and Arrant, D.Behavior ratings of emotionally disturbed children by teachers, parents, and school psychologists. Paper presented at the meeting of the American Educational Research Association, Toronto, Ontario, March, 1978.
5.
Serlin, R. C. and Kaiser, H. F.A computer program for item selection based on maximum internal consistency. EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT , 1976, 36, 757-759.
