Pretrial Predictors of Judgments in the O. J. Simpson Case

Five hundred seventy-eight community college and four-year state university students responded to questionnaires designed to assess judgments regarding O. J. Simpson's guilt, beliefs surrounding the case, general attitudes, and background information. Although African Americans were more likely to perceive Simpson as innocent than non–African Americans, correlation analyses revealed that, for the most part, the same predictors explained African Americans' and non–African American's judgments of guilt. Finally, set-wise hierarchical regression analyses indicated that case-related beliefs that Simpson abused Nicole Brown Simpson and that the system was biased against him accounted for more significant incremental variance than did demographic variables such as age and ethnicity, personal experiences, and general attitudes. The results suggested that the racial polarization emphasized in public polls does not reflect the diversity of beliefs that existed within both African American and European American populations.     

IMPROVED INFERENCE FROM RECAPTURE EXPERIMENTS WITH BEHAVIOURAL RESPONSE THROUGH MODELLING and AUXILIARY EXPERIMENTATION

Allowing for behavioural response in a recapture experiment involves a large reduction in the precision of estimating the unknown population size. Unless the number of individuals captured is very large, the model is of little use in practice. This paper studies the extent to which this efficiency loss can be reduced by modelling the behavioural response. The most dramatic improvements in efficiency are obtained by estimating the rate of the behavioural response from an intensive study of a small subset of the population. In many practical situations this may be a cost- and time-effective alternative to intensively sampling the entire population.     

Applications of Multinomial Dose-Response Models in Developmental Toxicity Risk Assessment

Reproductive and developmental anomalies induced by toxic chemicals may be identified using laboratory experiments with small mammalian species such as rats, mice, and rabbits. In this paper, dose-response models for correlated multinomial data arising in studies of developmental toxicity are discussed. These models provide a joint characterization of dose-response relationships for both embryolethality and teratogenicity. Generalized estimating equations are used for model fitting, incorporating overdispersion relative to the multinomial variation due to correlation among littermates. The fitted dose-response models are used to estimate benchmark doses in a series of experiments conducted by the U.S. National Toxicology Program. Joint analysis of prenatal death and fetal malformation using an extended Dirichlet-trinomial covariance function to characterize overdispersion appears to have statistical and computational advantages over separate analysis of these two end points. Benchmark doses based on overall toxicity are below the minimum of those for prenatal death and fetal malformation and may, thus, be preferred for risk assessment purposes.     

Smoothing spline estimation in varying-coefficient models

Summary.  Smoothing spline estimators are considered for inference in varying-coefficient models with one effect modifying covariate. Bayesian 'confidence intervals' are developed for the coefficient curves and efficient computational methods are derived for computing the curve estimators, fitted values, posterior variances and data-adaptive methods for selecting the levels of smoothing. The efficacy and utility of the methodology proposed are demonstrated through a small simulation study and the analysis of a real data set.     

Spectral analysis of combustion noise and flame pattern recognition

In many situations, flame patterns in a combustion chamber cannot be observed directly by using an electronic or optical probe. However, an experienced engineer can identify the burning process by listening to the noise that it generates. In this paper, we study acoustic characteristics of turbulent impinging flames by using spectral analysis and statistical pattern recognition. By experimenting with the ignition method, different flame patterns were generated in a laboratory. We find that each flame pattern can be characterized effectively by using the power spectrum of the noise and can be identified by using this information alone.     

Bayesian identifiability and misclassification in multinomial data

The authors consider the Bayesian analysis of multinomial data in the presence of misclassification. Misclassification of the multinomial cell entries leads to problems of identifiability which are categorized into two types. The first type, referred to as the permutation‐type nonidentifiabilities, may be handled with constraints that are suggested by the structure of the problem. Problems of identifiability of the second type are addressed with informative prior information via Dirichlet distributions. Computations are carried out using a Gibbs sampling algorithm.     

Stabilization,birth waves,and the surge in the elderly

This study examines the transition of a population to stability following a shift to a new fixed set of vital rates. Specifically, the authors develop a simple discrete population model and use it to derive an explicit solution for the birth trajectory. "The new vital rates interact with the population's initial age composition and generate birth waves whose amplitude and attenuation depend on the ratio of ultimate to initial growth and on the new pattern of stable net maternity. A greater change in growth and a later stable net maternity pattern produce larger fluctuations in the number of births. Stabilization begins at the youngest ages and proceeds upward. Sixty years after the shift, the birth waves have largely disappeared and the proportion under age 15 approximates the stable level implied by the new rates. Those patterns are manifest in the stabilization of both observed and Coale-Demeny model stable populations." (SUMMARY IN FRE)     

An optimized model for substitution of expatriate workforce in a Gulf-Council country: the Kuwaiti case

"This article is based on data from a research project carried out during 1992-1994 to achieve a replacement mechanism and a model for the substitution of expatriate labour by Kuwaiti nationals. Since Kuwait can readily enforce its Kuwaitization policy in the public sector, the presented model aims at reducing the share of non-Kuwaitis in that sector over five years. Published data on distribution of the workforce in the public sector by nationality indicate that the non-Kuwaiti share of the total workforce is 38 per cent. The majority of [migrant] workers are unskilled or semi-skilled and engaged in production, commerce and services. Sex ratios are unbalanced and workers exhibit a high rate of literacy...." (SUMMARY IN FRE AND SPA)     

Seven types of marriage: empirical typology based on enrich*

Using ENRICH, a computerized marriage assessment tool (Olson, Fournier & Druckman, 1986), data from 8,385 couples was collected across nine dimensions of their marriage. The data was analyzed in two phases-cluster structure seeking and classification phases-by three different clustering methods (inverse factor analysis, hierarchical agglomerative, and k-means cluster analysis). Seven types of marriage were identified: Devitalized couples (40%), Financially focused couples (11%), Conflicted couples (14%), Traditional couples (10%), Balanced couples (8%), Harmonious couples (8%), and Vitalized couples (9%). The multidimensional profiles are described in relation to global measure of marital satisfaction, demographic characteristics, and clinical and research implications.