In covariance structure analysis statistics like the modification index and the "t-values" can be used for modifying a model. A model with an acceptable fit might be simplified, whereas a rejected model might be expanded or otherwise altered. This paper describes the results of Monte Carlo research in which the usefulness of a number of statistics is examined when a wrongly specified factor analysis model is modified in one parameter. For the samples where the correct model was obtained after a first modification step, the empirical distribution of the parameter estimates is examined. The conclusion is that low power and sampling variability in the decision criteria used for model modification, can be a serious threat to the reliability and validity of the decision which model to retain.
CITATION STYLE
Luijben, T., Boomsma, A., & Molenaar, I. W. (1988). Modification of Factor Analysis Models in Covariance Structure Analysis a Monte Carlo Study (pp. 70–101). https://doi.org/10.1007/978-3-642-61564-1_5
Mendeley helps you to discover research relevant for your work.