The use of extreme groups to test for the presence of a relationship

Experimenters in psychology frequently investigate the relationship between two variables by selecting extreme groups on the first measure and comparing their mean scores on the second. This paper considers the efficacy of this procedure from the criterion of the power of the statistical tests. Optimal cutting points for the extreme groups are defined, and the power of the difference approach is compared to that of significance tests for the productmoment correlation coefficient.     

Shorter articles and notes two more visual theorems

The basis of the widely held opinion that the spectral sensitivities of the mechanisms determining trichromacy must be linearly related to the spectral mixture functions is examined, and a proof from simple assumptions is stated.

It is proved also that, on the van der Velden hypothesis of independent sensitive units, a spatial or temporal summation law of the form AIⁿ = c implies a frequency-of-seeing curve of the form Q = I—e^-KIn (Q = probability of detecting a stimulus of size A and intensity I; n, c and K are constants).     

A synthesis of two factor analyses of intermediate algebra

A battery of 18 tests of intermediate algebra and 20 reference tests was administered to two successive second-year algebra classes. Each battery was separately factor analyzed by Thurstone methods, and the two analyses were synthesized by the Tucker method. The five congruent factors obtained were identified as: Verbal Comprehension, Deductive Reasoning, Algebraic Manipulative Skill, Number Ability, and Adaptability to a New Task.This paper is a condensation of a thesis. The work was begun while the author was a Psychometrics Fellow of the Educational Testing Service. The work was further supported by Contract N6onr-270-20 of the Office of Naval Research and by Grant NSF G-642 of the National Science Foundation. The writer is indebted to Professors Harold Gulliksen and Ledyard R Tucker for their guidance throughout this study.     

Some implications of the logical calculus for empirical classes for social science methodology

An exposition of a calculus for empirical classes (CEC), one of the few attempts by logicians to deal with the problem of constructs and indicators, is presented. The CEC provides the groundwork for a formal structure for the situation in which individuals have a degree of membership in various classes rather than having either membership or nonmembership—a situation nearly always true in empirical research. The CEC is presented and its relation to various social science concepts is mentioned. An application of the CEC model to latent structure analysis (LSA) suggests alternatives to the local independence assumption including one called the local scale assumption, which has a close relation to a Guttman scale.     

Aversive control of self-injurious behavior in a psychotic boy

Two studies are reported which indicate how quickly and effectively chronic self-injurious behavior was controlled in a 9-yr-old blind psychotic boy. In the first study, the self-injurious responses were punished by contingent withdrawal of human physical contact. In the second study, response-contingent electric shock was employed.