APPROPRIATE SAMPLE-SIZE FOR COMPARING ALPHA-RELIABILITIES

In many measurement settings, it might be appropriate to test the sign ificance of the difference between the internal consistency reliabilit y coefficients of two competing measurement procedures. Determination of an adequate sample size is a crucial factor in the design of such s tudies. A graphical method was developed for determining sample size b ased on the power of Feldt's (1969) test of the difference between two values of Cronbach's alpha (alpha) coefficient. Implementation of thi s approach presumes that the researcher can specify a desired power fo r the statistical test against a particular alternative to the null hy pothesis.