Applied Psychological Measurement

Three verbal item types employed in standardized aptitude tests were administered in four formats—a conventional multiple-choice format and three formats requiring the examinee to produce rather than simply to recognize correct answers. For two item types—Sentence Completion and Antonyms—the response format made no difference in the pattern of correlations among the tests. Only for a multiple-answer open-ended Analogies test were any systematic differences found; even the interpretation of these is uncertain, since they may result from the speededness of the test rather than from its response requirements. In contrast to several kinds of problem-solving tasks that have been studied, discrete verbal item types appear to measure essentially the same abilities regardless of the format in which the test is administered.

To bridge the gap between computerized testing and information-processing-based measurement, a battery of computerized information-processing-based ability and preference measures was developed. The information-processing and preference measures and a battery of paper-and-pencil tests were administered to 64 college students. Although the internal-consistency reliabilities of the computerized information-processing measures were adequate, test-retest reliabilities were lower than desirable for ability measures. The computerized information-processing measures possessed moderate convergent validity but had low correlations with traditional paper-and-pencil measures. Of the computerized preference measures, the most promising results were obtained with the Stimulus Pace measure. A major problem with the use of the computerized information-processing measures in applied settings would be administration time, as the battery took approximately 4 hours. In addition, problems with the stability of results over time and substantial practice effects suggest that even longer testing sessions would be required to obtain reliable measures. Although information-processing measures of short-term memory have, at best, low correlations with traditional intelligence tests, their ability to predict real-world tasks has yet to be sufficiently researched.

An integrated package of statistics is described for measuring the relationship between binary dominance data, such as choices, and predictor variables that measure the objects or stimuli. The degree of fit between predictors and choices is defined, and procedures for determining the maximum possible fit and minimum acceptable fit are described. The statistics are applied, for illustrative purposes, to a practical data set.

Skinner (1979) has described a generalized principal components model for classification research that assumes interval or quasi-interval data. First, a parsimonious set of typal dimensions is sought through a multiple replication design, and then relatively homogeneous subgroups are identified within this low dimensional space. The purpose of this paper is to describe preliminary transformations whereby the model may be extended to situations where the data are of either categorical or rank-order metric.

A path analytic technique is described for obtaining separate estimates of variables that are normally confounded. The particular problem involves ascertaining the relative contributions of the instructor and the course being taught in determining student ratings of teaching effectiveness. A series of six different path analytic models were used to estimate teacher and course effects, along with a variety of other parameters. The best model indicated that the effect of the teacher is about five times as large as the effect of the course and that the difference is even larger for components such as Overall Instructor and Instructor Enthusiasm. In contrast to the student rating items, background/demographic variables such as class size, students' prior subject interest, and reason for taking a course were largely a function of the course rather than the instructor.

A translated version of the Comrey Personality Scales was administered to 185 male applicants for motor vehicle operator's license in Israel after special measures were taken to reduce response distortion. Total scores were computed for these subjects over each of the 40 homogeneous item subgroups that define the eight personality factors in the taxonomy underlying the Comrey Personality Scales. Factor analysis of the intercorrelations among these 40 subvariables resulted in substantial confirmation of seven of the eight hypothesized factors. Failure of the eighth factor to emerge may have been due to higher average scores and lower standard deviations for the item groups defining this particular factor, possibly caused by the special conditions under which the subjects were tested. The overall results of this study provide further evidence confirming the robustness of the taxonomy of personality traits underlying the Comrey Personality Scales across language and cultural boundaries.

A prototype measure of interpersonal competence, designed to measure effectiveness in dealing with other people, was developed-the Interpersonal Competence Instrument (ICI). The ICI is based on the videotape presentation of scenes of subordinates talking to a superior in a business setting. The examinee takes the role of the superior, his or her tape-recorded replies are assessed for effectiveness and originality, and his or her written judgments are evaluated for accuracy. In a pilot study (1) the three scores for the ICI were reliable, in terms of both interrater agreement and internal consistency; (2) the effectiveness and originality scores for replies were only moderately correlated with the accuracy scores for judgments, but the two replies scores were highly intercorrelated ; and (3) the correlations of the scores with background measures and other instruments, including measures of verbal ability and accuracy in social perception, generally supported the ICI's construct validity.

A simple method is introduced to test the dimensionality axiom in the Rasch model. The method consists of a suitable partitioning of the data set. This partitioning is based on the responses to some of the items being investigated. The items used for this purpose are called the external criterion items. data are presented indicating the effectiveness of the method in instances where the traditional test procedures fail.

Three models are presented that account for the effects of speed and precision in mental test scores as measured by time-limit intelligence tests. To estimate precision, it is shown that the Rasch model— and, as a special case, the binomial error model —can be used, focusing on the number of items correct and the number of items attempted (usually considered as estimators of these effects). To estimate speed, a model called the Poisson-Erlang model is presented. It is shown that speed can be analyzed into two components: processing time and distraction time. Parameters of the Poisson-Erlang model are used to estimate these components. An outline is given of a new method for analyzing time-limit tests, combining the different models. In addition, it is shown that the Poisson-Erlang model can be used to account for response latencies commonly observed in mental concentration tests.

Some characteristics of Hubert's Г, as a measure of nominal scale response agreement, are shown, including the characteristic that in a contingency table with equal frequencies its value will normally not be zero. By making a slight modification of its definition, some of these characteristics can be eliminated. As another alternative, the J-index is suggested. It is closely related to Г but does not have the same problematic characteristics. Some asymptotic variance formulas for the J-index are given, together with a numerical example.