Statistical procedures are presented for determining ordinal and disordinal aptitude-treatment interactions with linear and curvilinear data. The paper presents a method for testing the homogeneity of group regressions for a single aptitude and provides models for expanding this test to linear and curvilinear regression planes. Procedures are…

This paper describes several situations in which generalization of statistical results is not possible by representative sampling but which is attempted using corrections for selection of groups. The situations include hiring, admissions, differential classification, guidance, test score equating, and test score scaling. Evidence of inaccuracies…

The nature of the relations between traditional psychometric and Piagetian instruments is analyzed, in order to provide information relevant to the question of which type of test or combination of them will provide the most useful information to those seeking to construct and maintain optimal learning environments. Four hypotheses are posed: (1)…

Using post-secondary vocational and technical education students as the populations, the objectives of this project were to determine: (1) the ability of standardized instruments to predict the various criteria of success, (2) the relative ability of the different instruments to predict each criterion of success, and (3) which sub-set of all of…

A COMPARISON WAS MADE OF THE RELATIVE ACCURACY OF PREDICTION OF COLLEGE FRESHMAN GRADE POINT AVERAGES FROM SCHOLASTIC APTITUDE TEST (SAT) SCORES IN PREDOMINANTLY NEGRO AND PREDOMINANTLY WHITE SOUTHERN COLLEGES. DATA PUBLISHED BY A SOUTHERN STATE UNIVERSITY SYSTEM ON TESTS USED IN DETERMINING ELIGIBILITY FOR COLLEGE ADMISSION WERE ANALYZED AND…

Using data collected by the International Association for the Evaluation of Educational Achievement (IEA), the authors of this study examined the reading achievement of 14-year-old boys in India and England. They sought to determine the factors involved in the academic achievement of these boys in the natural sciences. Factors studied, in addition…

Using career histories of academic psychologists, a study that investigated sex differences in patterns of geographic location and mobility, predictors of mobility, and the outcomes of geographic location and mobility is described. Women tend to be less mobile than men immediately after receiving their doctorates. (Author/MLW)

Describes a circulation model for academic research libraries which uses the mixed Poisson model, incorporating ageing of library materials, to predict future use of monographs and to suggest weeding procedures based on frequency of circulation. Longitudinal studies are examined and statistical details are appended. (Author/LRW)

Standardized tests rely on communicative behavior. Incongruities between the language of the test giver and the test taker can result in bias. Data on communications should be consulted so that tests allow for linguistic and cultural differences. This is the only way the abilities of Blacks can be accurately assessed. (VM)

Data on the early prediction of learning problems was summarized by a meta analysis of 58 studies reporting correlations between measures administered in kindergarten or first grade and later reading achievement. The best single predictors of achievement were attention-distractibility, internalizing behavior problems, and language variables.…

Most British universities accept students conditional upon A-level grades and place little reliance on recommendations. A study of social science undergraduates shows the importance of attitudinal variables and the headmaster's report in predicting success at the university. More attention should be paid to these reports. (IS)

Examines whether individual intelligence tests such as the WISC-R are biased against Hispanic school-aged children. Discusses three common but faulty notions of test bias, and advances a psychometric definition of bias. Analyzes evidence regarding external and internal validity. Presents guidelines for intellectual assessment of bilingual…

An investigation was made to determine the increase in predictive efficiency attained by adding noncognitive variables to cognitive variables in predicting clinical performance of residents. It was found that a combination functions much better than any individual variables or even any specific class of variables in predicting resident clinical…

The theory of culturally biased test scores is discussed, in terms of both the Bakke case and the theory's broader societal implications. Literature addressing the problem of test bias is reviewed. Remedies for predictive invalidity are proposed. The importance of thorough documentation in court litigation concerning this issue is stressed.…

Topics concerning latent trait theory are addressed: (1) dimensionality of latent space, local independence, and item characteristic curves; (2) models--equations, parameter estimation, testing assumptions, and goodness of fit, (3) applications test developments, item bias, tailored testing and equating; and (4) advantages over classical…