Correlational Analyses of Test-Retest Data with a Thirty-Year Intertrial Interval

In recent years there has been a marked increase in the application of the methods of factor analysis to data associated with studies of learning phenomena or of practice effects. The problems are usually posed as investigations of changes in factorial composition as a function of practice with the variables of the correlation matrix including two or more trials on one or more tasks, or two or more parallel forms of some test. The first purpose of this paper is to present an application of a recently developed procedure for analyzing such correlational data. (2) In contrast to the analyses previously offered, the present procedure is logically correct and computationally feasible