Ronald L. Flaugher

The Use Of Analysis Of Covariance Structures For Comparing The Psychometric Properties Of Multiple Variables Across Populations

It is common practice to assume that the dependent variables in differential prediction studies, and analysis of variance and co-variance designs are characterized by certain psychometric properties which are invariant across the subgroups of interest. More specifically, the accuracy of the results of such analyses depends on the assumption that the dependent variables are measuring the constructs in the same metrics with equivalent reliabilities across all subgroups. Systematic procedures are outlined for testing these assumptions.

A Fixed Length Optimal Test Battery for Colleges Characterized by Diverse Aptitude Levels

The diversity of modem college populations makes it unlikely that any particular predictor of academic success could be employed as a selection device with equal success at all colleges. Rather, in view of this diversity it would appear that the most satisfactory predictive tool would itself be diverse in content, and in addition, that the diversity would be capable of manipulation; that is, the various part-scores should be reported, which would enable the using institutions to weight the various types of content in a manner which had been found optimal for the prediction of success in their particular curricula. This report describes an attempt to devise such an optimal test battery, by validating a number of promising experimental aptitude measures across a wide range of college populations, in an attempt to construct a single, multiple score test battery of diverse content, to be used as a selection device at all colleges. The existing, relatively homogeneous, two-score Scholastic Aptitude Test (SAT) was employed as a standard of comparison. By increasing the variety of content from the Verbal and Mathematics material in the SAT, it was anticipated that useful increases