A Summary and Commentary on D. and S. Premack’s Original Intelligence

The Analysis of Verbal Behavior -     

Flexible models for non-equidispersed count data: comparative performance of parametric models to deal with underdispersion

AStA Advances in Statistical Analysis - Count data as response variables are commonly modeled using Poisson regression models, which require equidispersion, i.e., equal mean and variance. However,...     

Unconstrained parametrizations for variance-covariance matrices

The estimation of variance-covariance matrices through optimization of an objective function, such as a log-likelihood function, is usually a difficult numerical problem. Since the estimates should be positive semi-definite matrices, we must use constrained optimization, or employ a parametrization that enforces this condition. We describe here five different parametrizations for variance-covariance matrices that ensure positive definiteness, thus leaving the estimation problem unconstrained. We compare the parametrizations based on their computational efficiency and statistical interpretability. The results described here are particularly useful in maximum likelihood and restricted maximum likelihood estimation in linear and non-linear mixed-effects models, but are also applicable to other areas of statistics.     

Personal heroes,religion, and transcendental metanarratives

With the increased sociological interest in popular culture, many studies have examined the hero types lauded by the media from situation comedies to movies, books, and magazines. Few studies, however, have examined who, if anybody, actual individuals identify as personal heroes. To the extent that the hero identification of individuals has been examined at all, it has generally been the hero identification of children and adolescents that has been studied. The study of heroes is important because heroes are one indicator of who we are and what we stand for. That is partly what motivates the recent attention to the media's identification of heroes. Yet while the media represent a very visible aspect of culture, who individuals privately cite as their heroes is, although less visible, just as much a part of who we are as a culture. Accordingly, this paper reports on findings from two telephone surveys conducted in Philadelphia that, among other questions pertaining to the meaning of life, asked adults over 18 whether they had any heroes and if so who those heroes were. The tendency to identify with heroes was found to be related to transcendental concerns with the meaning of life and to religiosity. Overall, the pattern of findings discloses an unstudied dimension of cultural disenchantment.     

The Criminalization of Drug Use

Sociological Forum -     

New Estimates of Undocumented Mexican Migration and the Probability of Apprehension*

Using a new source of data, we estimate the probability of apprehension among Mexican migrants attempting to cross into the United States without documents. Over the period 1965-1989 we found an average apprehension probability of .35, confirming earlier estimates. We then applied annual probabilities to estimate the gross volume of undocumented Mexican migration and adjusted these figures to derive estimates of the net undocumented inflow.     

Re-Assessing the Relationship between High School Sports Participation and Deviance: Evidence of Enduring, Bifurcated Effects

Despite its long-standing popular appeal, the idea that athletic activity is a deterrent to crime and delinquency suffers from a distinct lack of empirical support. This article tests the hypothesis that the relationship between high school sports participation and deviance varies by both type of deviant behavior and level of athletic involvement. The analysis is based upon longitudinal data focusing on the effects of involvement in high school sports, the country's largest institutional setting for youth sports participation, in early adulthood. We find that the relationship between athletic involvement and deviance varies significantly depending upon the deviant behaviors examined. Specifically, we find that shoplifting decreases with sports participation, while drunken driving increases. Moreover, these effects extend further into the life course (age 30) than has been demonstrated in any previous study and hold across all our measures of sports participation. Several potential explanatory mechanisms are evaluated. The implications of these enduring, bifurcated effects are discussed.