On tests for correlated proportions in the presence of incomplete data

This paper proposes test statistics based on the likelihood ratio principle for testing equality of proportions in correlated data with additional incomplete samples. Powers of these tests are compared through Monte Carlo simulation with those of tests proposed recently by Ekbohm (based on an unbiased estimator) and Campbell (based on a Pearson-Chi-squared type statistic). Even though tests based on the maximum likelihood principle are theoretically expected to be superior to others, at least asymptotically, results from our simulations show that the gain in power could only be slight.     

Smoking and pain--a method of limits and sensory decision theory analysis

The effects of tobacco smoking on responses to electrical stimulation were studied according to a Method of Limits (ML) threshold analysis and a Sensory Decision Theory (SDT) analysis. For the ML procedure, Detection Threshold (DT), Pain Threshold (PT) and Tolerance Level (TL) measures were obtained. For the SDT procedure, nonparametric estimates of capacity to discriminate between stimulus intensities (P(A)) and response criterion (B) were calculated. There was no main effect of tobacco smoking on responses to electrical stimulation. Males had consistently higher ML thresholds than females in both the NS and S condition. Males also tended to increase in DT and PT after smoking. From a comparison between the effects of smoking on ML and SDT measures it was suggested that PT is related mainly to sensory factors and TL to response factors.     

Constrained classification: The use of a priori information in cluster analysis

In many classification problems, one often possesses external and/or internal information concerning the objects or units to be analyzed which makes it appropriate to impose constraints on the set of allowable classifications and their characteristics. CONCLUS, or CONstrained CLUStering, is a new methodology devised to perform constrained classification in either an overlapping or nonoverlapping (hierarchical or nonhierarchial) manner. This paper initially reviews the related classification literature. A discussion of the use of constraints in clustering problems is then presented. The CONCLUS model and algorithm are described in detail, as well as their flexibility for use in various applications. Monte Carlo results are presented for two synthetic data sets with appropriate discussion of the resulting implications. An illustration of CONCLUS is presented with respect to a sales territory design problem where the objects classified are various Forbes-500 companies. Finally, the discussion section highlights the main contribution of the paper and offers some areas for future research.We wish to thank C. Mallows and J. D. Carroll for some helpful technical discussion and L. Clark and D. Art for their valuable computer assistance. We also wish to thank H. Pollak, R. Gnanadesikan, and J. Kettenring for their thorough reviews of a previous draft of this paper. Finally, we acknowledge helpful comments of the editor and two anonymous reviewers.     

The St. Pauls' riot: An explanation of the limits of crowd action in terms of a social identity model

The paper contains a detailed study of the St. Pauls' riots of April 1980. Particular attention is paid to the limits of participation in the event and the limits of crowd action. It is argued that these limits show clear social form and cannot be explained in terms of the individualistic theories that dominate crowd psychology. Instead a model of crowd behaviour based on the social identity model is advanced to account for the observations. It is concluded that crowd behaviour is more sophisticated and creative than hitherto allowed and that the neglect of this field should be remedied.     

Acoustic and semantic similarity effects on repetition avoidance in produced sequences

The question of whether repetition avoidance in sequential response production depends on the phonetic or the semantic encoding of previous responses was investigated by varying the acoustic and semantic similarity among the response alternatives. The results indicated that acoustic similarity affected repetition avoidance with six alternative words and a production rate of one per second, but not with four alternative letters and a rate of one per 2 sac. Semantic similarity between words was also studied, and was not seen to affect repetition avoidance. Results were explained by means of a model in which comparisons between a memory set of admissible responses and a memory set of recent responses are made at a phonetic level of response representation.     

Depressed mood and environmental mastery as potential pathways linking family relationship quality and disease self-management for African Americans with hypertension

African Americans are at significantly greater risk of hypertension and worse cardiovascular outcomes than other racialized groups, yet hypertension intervention effects remain limited. Thus, it is necessary to understand the potential mechanisms whereby interventions may be more effectively targeted to improve health. Supported by prior research evidence and guided by the Biobehavioral Family Model, this study examined associations between family relationship quality, psychological wellbeing, and self-management behaviors for African Americans with hypertension. Data were pooled from three Midlife Development in the U.S. projects, resulting in a sample of 317 African Americans (63.4% female, M_age = 53.32) with self-reported high blood pressure in the past 12 months. We tested four cross-sectional multiple mediator models, with depressed mood and environmental mastery mediating associations between family strain and exercise, smoking, problematic alcohol use, and stress-eating. Environmental mastery mediated the association between greater family strain and decreased odds of achieving recommended exercise levels; greater odds of reporting problematic alcohol use; and greater stress-eating. Though family strain was associated with depressed mood in each model, this variable did not serve as an indirect pathway to self-management behaviors. Family strain, and the potential pathway identified via environmental mastery, may be a meaningful predictor of disease self-management for African Americans with hypertension. Longitudinal studies are needed to examine directionality and to support intervention trials for improving self-management and hypertension outcomes.