The purpose of this study was to examine the effects on Cronbach coefficient alpha, an estimate of internal consistency reliability, of altering the number and type of item-response choices on measures administered to two independent samples (ns, 492 and 730). An increase in the number and type of response choices (from true/false format to four-choice Likert-type format) significantly increased the internal consistency reliability estimate.
Get full access to this article
View all access options for this article.
References
1.
CronbachL. J. (1951) Coefficient alpha and the internal structure of tests. Psychometrika, 16, 297–334.
2.
FeldtL. S. (1969) A test of the hypothesis that Cronbach's alpha or Kuder-Richardson coefficient twenty is the same for two tests. Psychometrika, 34, 363–373.
3.
GreenK.SaxG., & MichaelW. B. (1982) Validity and reliability of tests having differing numbers of options for students of differing levels of ability. Educational and Psychological Measurement, 42, 239–245.
4.
HakstianA. R., & WhalenT. E. (1976) A k-sample significance test for independent alpha coefficients. Psychometrika, 41, 219–231.
5.
LordF. M. (1977) Optimal number of choices per item: a comparison of four approaches. Journal of Educational Measurement, 14, 33–38.
6.
TverskyA. (1964) On the optimal number of alternatives at a chance point. Journal of Mathematical Psychology, 1, 386–391.
