A method of analysis is developed which accounts for whatever variance is present in the responses to test items, additive, configural or the two combined. The method is applied to successive column matrices which report frequencies or endorsements by categories of subjects to answer alternative sets of test items. Approaches are included which…

Research supported by Public Health Research Grant MH-10274-4 from the National Institute of Mental Health.

In this analysis of the structure of the faculty characterizations of students, the same data was used as in the initial study. An oblique solution was obtained by applying the Promax method of Hendrickson and White to the previous Equamax solution. This yielded 18 factors. From intercorrelations among the factor axes, a principal axes procedure…

This report, a continuation of the study described in TM 000 174 and TM 000 176, employs identical data and similar methods to determine the nature of desirability separate and apart from the rater's perception of the student's academic performance (rather than his actual performance). The results show an absorption in the faculty perception of…