A test is proposed for determining whether several scores in a test profile, considered simultaneously, are unusual or not. The test involves the evaluation of a Wishart (multivariate chi-square) distribution. When many tests are made on one profile, the probability level can be adjusted with the Bonferroni correction. This test can be regularly evaluated in computer-based test interpretation programs. An example from a new test of career decision making is given.
Get full access to this article
View all access options for this article.
References
1.
Anderson, T. W. (1984). An introduction to multivariate statistical analysis (2nd ed.). New York: Wiley.
2.
Harren, V. A., & Buck, J. N. (1985). Assessment of career decision making. Los Angeles: Western Psychological Services.
3.
Huba, G. J. (in press-a). A frequency-based test of valid responding in questionnaires. Educational and Psychological Measurement.
4.
Huba, G. J. (in press-b). Simplified formula for bivariate uniqueness analysis. Educational and Psychological Measurement.
5.
Larzelere, R. E., & Mulaik, S. A. (1977). Single-sample tests for many correlations. Psychological Bulletin, 84, 557-569.
6.
Tatsuoka, M. M. (1971). Multivariate analysis. New York: Wiley.
7.
Zachary, R. A., & Huba, G. J. (in press). Simplified formula and table for the unusualness of combinations of subtest scores on the Shipley Institute of Living Scale. Journal of Clinical Psychology.
