This article introduces a procedure for estimating reliability in which equivalent halves of a given test are systematically created and then administered a few days apart so that transient error can be included in the error calculus. The procedure not only estimates complete reliability (taking into account both specific-factor error and transient error) but also can estimate partial reliability (taking into account only specific-factor error). Scores from 6 different measuring instruments were analyzed with the procedure. The results indicate that the magnitude of transient error in real data can range from nonexistent to very large. It follows that traditional reliability estimates, using nonstaggered procedures, are inflated to the extent that transient error is present.

This article introduces and illustrates a procedure for aggregating data from several factor analyses in a meta-analysis. The central idea is to combine the correlation matrices first and then perform a new factor analysis. Special attention is given to the handling of general factors in data sets and to the use of correlations corrected for attenuation. Bushman, Cooper, and Lemke (1991) recently introduced a procedure for comparing factor loadings derived in two samples of subjects. When there are more than two samples, the procedure is repeated for all possible pairs of samples. Essentially, the method determines the level of congruence between corresponding factors and requires knowledge only of the factor matrix, which, as the authors pointed out, is one of its major attractions. However, although Bushman el al.'s (1991) use of a method for determining congruence among factors has its merits, ordinarily only zero-order correlations can legitimately be cumulated across studies (Hunter & Schmidt. 1990, pp. 503-504). Furthermore, the congruence method, following Thompson's (1989) criteria for determining whether a study should be included in such comparisons, requires that, in the results being compared, the same variables and no additional variables appear, the same extraction method be used, and the same transformation or rotation method be followed. When correlations are aggregated, however, these requirements, as well as the additional requirement that the same number of factors be extracted, are irrelevant.

No abstract

No abstract