Correctness of Kruskal's algorithms for monotone regression with ties

Kruskal has proposed two modifications of monotone regression that can be applied if there are ties in nonmetric scaling data. In this note we prove Kruskal's conjecture that his algorithms give the optimal least squares solution of these modified monotone regression problems. We also propose another (third) approach for dealing with ties.Comments by Dr. J. B. Kruskal have been most helpful.     

BEHAVIOR ANALYSIS APPLIED TO ENVIRONMENTAL/ECOLOGICAL PROBLEMS; A REVIEW1

Recent applications of operant technology, including the manipulation of environmental conditions and response consequences, have been directed toward the improvement of man-environment relations. This document summarizes the research designs, procedures, results, and conclusions of these recent behavioral interventions for ecological rebalance. Each of the 32 studies reviewed was undertaken since 1970; all studies were relatively successful in changing the probability of an ecology-related response; all studies incorporated basic methodologies applicable for large-scale, community programs; most of the investigations were conducted in field settings (e.g., college campuses, grocery stores, mobile-trailer parks, homes, movie theaters, public campgrounds, and a football stadium). Several of the studies are as yet unpublished. Sources for receiving documentation of the unpublished research are provided in this document. About 50% of the investigations reviewed were designed to influence behaviors related to environmental litter; the others were of behavior-modification programs that substantially increased bus-ridership, decreased lawn-trampling, promoted the purchase of drinks in returnable rather than throwaway containers, initiated a recycling process, or reduced energy consumption. Essentially, the interventions were either preventive in nature (i.e., designed to discourage environment-destructive behaviors before they occur), or remedial (i.e., designed to encourage behaviors that correct an existing environmental problem). Usually, the preventive measures emphasized responses priming (or prompting), while the corrective measures applied some form of positive reinforcement. Response priming was accomplished with modelling techniques, or with written and/or verbal prompts presented either publicly or on a personal, one-to-one basis. Among the positive reinforcement procedures were field applications of token economies, lottery systems, feedback programming, and intergroup contests, as well as individual contingency contracting. Some experimental designs provided for comparisons between the behavioral effects of response priming and positive reinforcement.     

The development of sensitivity to cast and attached shadows in pictures as information for the direction of the source of illumination

The development of the perception of cast and attached shadows as information in pictures for the direction of the light source was studied with children in kindergarten, third and sixth grades, and adults in college. Subjects viewed photographs of objects under four different positions of illumination, with either cast or attached shadows alone, or with both present. Error in angular displacement from the correct position of the light source was 76.5° for kindergarten children, 40.5° for those in the third grade, 34.9° for those in the sixth, and 18.0° for college students. Neither position of light nor type of object affected performance. Results are discussed in the context of a developmental hypothesis of changing interpretation of the relations between pictorial and nonpictorial space from childhood to adolescence.     

Emotional Intelligence: Toward a Consensus of Models and Measures

This article outlines the many different ways that emotional intelligence (EI) has been conceptualized, measured, and used from the early antecedents of emotional abilities such as facial expression research to the recent multimedia assessment paradigms. The divide between models describing EI as a character trait versus modeling EI as a form of information processing or knowledge is described, with both kinds of models evaluated based on theory and empirical evidence. It is concluded that the latter type of model, exemplified by the four-branch hierarchical model of EI, is the only logical construct to bear the label ‘EI’. Potential emendations to the way EI is currently conceptualized and measured are discussed, with this review covering emotion recognition assessments, situational judgment tests, and multimedia assessments such as the empathic agent paradigm. The article concludes with a suggested agenda for future research in the EI field.