When errors of measurement are positively correlated, coefficient alpha may overestimate the “true” reliability of a composite. To reduce this inflation bias, Komaroff (1997) has proposed an adjusted alpha coefficient, ak. This article shows that ak is only guaranteed to be a lower bound to reliability if the latter does not include correlated error. If one's definition of reliability includes correlated error, then an alternative adjusted alpha, ar, is suggested, which will always be a lower bound. Index terms: coefficient alpha, adjusted alpha, correlated errors, lower bound, reliability
Get full access to this article
View all access options for this article.
References
1.
Abramowitz, M., & Segun, I. A. (Eds.). (1986). Handbook of mathematical functions. New York: Dover.
2.
Guttman, L. (1945). A basis for analyzing test-retest reliability. Psychometrika, 10, 255-282.
3.
Guttman, L. (1953). Reliability formulas that do not assume experimental independence. Psychometrika, 18, 225-239.
4.
Komaroff, E. (1997). Effect of simultaneous violations of essential tau equivalence and uncorrelated errors on coefficient alpha. Applied Psychological Measurement, 21, 337-348.
5.
Lord, F. M., & Novick, R. (1968). Statistical theories of mental test scores. Reading, MA: Addison-Wesley.
6.
Raykov, T. (1998). Coefficient alpha and composite reliability with interrelated nonhomogeneous items. Applied Psychological Measurement, 22, 375-385.
7.
Raykov, T. (2001). Bias of coefficient a for fixed congeneric measures with correlated errors. Applied Psychological Measurement, 25, 69-76.
8.
Rozeboom, W. W. (1966). Foundations of the theory of prediction. Homewood, IL: Dorsey.
9.
Spearman, C. (1910). Correlation calculated fromfaulty data. British Journal of Psychology, 3, 271-295.
10.
Zimmerman, D. W., Zumbo, B. D., & Lalonde, C. (1993). Coefficient alpha as an estimate of reliability under violation of two assumptions. Educational and Psychological Measurement, 53, 33-49.
