Two composite reliability measures, coefficient alpha and coefficient omega with unit weights (otherwise known as construct reliability), are commonly used in structural equations modeling. However, a third measure, omega with unequal weights, is more theoretically appropriate. The potential for bias in reliability estimation and for errors in item selection when alpha or unit-weighted omega are used are explored under a variety of simulated conditions. The results suggest that composite reliability may be used as an assessment tool, but should not be used as an item selection tool in structural equations modeling.
Get full access to this article
View all access options for this article.
References
1.
Allen, M. P. (1974). Construction of composite measures by the canonical-factor-regression method. In H. L. Costner (Ed.), Sociological methodology (pp. 51-78). San Francisco: Jossey-Bass.
2.
Armor, D. J. (1974). Theta reliability and factor scaling. In H. L. Costner (Ed.), Sociological methodology (pp. 17-50). San Francisco: Jossey-Bass.
3.
Bagozzi, R. P. , & Yi, Y. (1988). On the evaluation of structural equation models. Journal of the Academy of Marketing Science, 16, 74-94.
4.
Brennan, R. L. (1992). Elements of generalizability theory. Iowa City, IA: ACT.
5.
Cortina, J. M. (1993). What is coefficient alpha? An examination of theory and applications. Journal of Applied Psychology, 78, 98-104.
6.
Cronbach, L. J. (1951). Coefficient alpha and the internal structure of tests. Psychometrika, 16, 297-334.
7.
Cronbach, L. J. , Gleser, G. C., Nanda, H., & Rajaratnam, N. (1972). The dependability of behavioral measurements: Theory of generalizability for scores and profiles. New York: Wiley.
8.
Fornell, C. , & Larcker, D. F. (1981). Structural equations models with unobservable variables and measurement error: Algebra and statistics. Journal of Marketing Research, 18, 39-50.
9.
Gerbing, D. W. , & Anderson, J. C. (1988). An updated paradigm for scale development incorporating unidimensionality and its assessment. Journal of Marketing Research, 25, 186-192.
10.
Greene, V. L. , & Carmines, E. G. (1980). Assessing the reliability of linear composites. In K. F Schuester (Ed.), Sociological methodology (pp. 160-175). San Francisco: Jossey-Bass.
11.
Hattie, J. A. (1985). Methodology review: Assessing unidimensionality of tests and items. Applied Psychological Measurement, 9, 139-164.
12.
Heise, D. R. , & Bohrnstedt, G. W. (1970). Validity, invalidity, and reliability. In E. F. Borgatta & G. W. Bohrnstedt (Eds.), Sociological methodology (pp. 104-129). San Francisco: Jossey-Bass.
13.
Hoyle, R. H. , & Lennox, R. D. (1991). Latent structure of self monitoring. Multivariate Behavioral Research, 26, 511-540.
14.
Jarjoura, D. (1983). Best linear prediction of composite universe scores. Psychometrika, 48, 525-539.
15.
Kenny, D. A. (1979). Correlation and causality. New York: Wiley.
16.
Mathcad 3.1 [Computer program]. (1992). Cambridge, MA: MathSoft Inc.
17.
Nunnally, J. C. (1978). Psychometric theory (2nd ed.). New York: McGraw-Hill.
18.
Reuterberg, S. , & Gustafsson, J. (1992). Confirmatory factor analysis and reliability: Testing measurement model assumptions. Educational and Psychological Measurement, 52, 795-811.
19.
Werts, C. E. , Linn, R. L., & Jöreskog, K. G. (1974). Interclass reliability estimates: Testing structural assumptions. Educational and Psychological Measurement, 34, 25-33.
20.
Zimmerman, D. W. , Zumbo, B. D., & Lalonde, C. (1993). Coefficient alpha as an estimate of test reliability under violation of two assumptions. Educational and Psychological Measurement, 53, 33-49.
