Significance Testing and Efficiency in Lisrel Measurement Models

Abstract
Traditionally, LISREL confirmatory factor analytic measurement models are tested against a null model of total independence. Using randomly generated factors in a matrix of 46 aptitude tests, this investigation has shown that this approach is unlikely to reject even random factors. An alternative null model, based on a single general factor, is suggested. In addition, an index of model efficiency is introduced as a helpful adjunct to contemporary indices of overall fit. The helpfulness of these procedures is demonstrated in a confirmatory factor analysis based on Guilford's structure-of-the-intellect model.