Premium
A Comparison of Tests for Equality of Two or More Independent Alpha Coefficients
Author(s) -
Kim Seonghoon,
Feldt Leonard S.
Publication year - 2008
Publication title -
journal of educational measurement
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.917
H-Index - 47
eISSN - 1745-3984
pISSN - 0022-0655
DOI - 10.1111/j.1745-3984.2008.00059.x
Subject(s) - type i and type ii errors , statistics , mathematics , alpha (finance) , variance (accounting) , test (biology) , power (physics) , econometrics , psychometrics , paleontology , construct validity , physics , accounting , quantum mechanics , business , biology
This article extends the Bonett (2003a) approach to testing the equality of alpha coefficients from two independent samples to the case ofm ≥ 2 independent samples. The extended Fisher‐Bonett test and its competitor, the Hakstian‐Whalen (1976) test, are illustrated with numerical examples of both hypothesis testing and power calculation. Computer simulations are used to compare the performance of the two tests and the Feldt (1969) test (for m = 2) in terms of power and Type I error control. It is shown that the Fisher‐Bonett test is just as effective as its competitors in controlling Type I error, is comparable to them in power, and is equally robust against heterogeneity of error variance.