Rc. Maccallum et al., POWER ANALYSIS AND DETERMINATION OF SAMPLE-SIZE FOR COVARIANCE STRUCTURE MODELING, Psychological methods, 1(2), 1996, pp. 130-149
A framework for hypothesis testing and power analysis in the assessmen
t of fit of covariance structure models is presented. We emphasize the
value of confidence intervals for fit indices, and we stress the rela
tionship of confidence intervals to a framework for hypothesis testing
. The approach allows for resting null hypotheses of not-good fit, rev
ersing the role of the null hypothesis in conventional tests of model
fit, so that a significant result provides strong support for good fit
. The approach also allows for direct estimation of power, where effec
t size is defined in terms of a null and alternative value of the root
-mean-square error of approximation fit index proposed by J. PI. Steig
er and J. M. Lind (1980). It is also feasible to determine minimum sam
ple size required to achieve a given level of power for any test of fi
t in this framework. Computer programs and examples are provided for p
ower analyses and calculation of minimum sample sizes.