An empirical Bayes' procedure for ranking players in Ryder Cup golf

We describe a model to obtain strengths and rankings of players appearing in golf's Ryder Cup. Obtaining rankings is complicated because of two reasons. First, competitors do not compete on an equal number of occasions, with some competitors appearing too infrequently for their ranking to be estimated with any degree of certainty, and second, different competitors experience different levels of volatility in results. Our approach is to assume the competitor strengths are drawn from some common distribution. For small numbers of competitors, as is the case here, we fit the model using Monte-Carlo integration. Results suggest there is very little difference between the top performing players, though Scotland's Colin Montgomerie is estimated as the strongest Ryder Cup player.     

A Bayesian Model and Stochastic Exposure (Dose) Estimation for Relative Exposure Risk Comparison Involving Asbestos‐Containing Dropped Ceiling Panel Installation and Maintenance Tasks

Assessing exposures to hazards in order to characterize risk is at the core of occupational hygiene. Our study examined dropped ceiling systems commonly used in schools and commercial buildings and lay‐in ceiling panels that may have contained asbestos prior to the mid to late 1970s. However, most ceiling panels and tiles do not contain asbestos. Since asbestos risk relates to dose, we estimated the distribution of eight‐hour TWA concentrations and one‐year exposures (a one‐year dose equivalent) to asbestos fibers (asbestos f/cc‐years) for five groups of workers who may encounter dropped ceilings: specialists, generalists, maintenance workers, nonprofessional do‐it‐yourself (DIY) persons, and other tradespersons who are bystanders to ceiling work. Concentration data (asbestos f/cc) were obtained through two exposure assessment studies in the field and one chamber study. Bayesian and stochastic models were applied to estimate distributions of eight‐hour TWAs and annual exposures (dose). The eight‐hour TWAs for all work categories were below current and historic occupational exposure limits (OELs). Exposures to asbestos fibers from dropped ceiling work would be categorized as “highly controlled” for maintenance workers and “well controlled” for remaining work categories, according to the American Industrial Hygiene Association exposure control rating system. Annual exposures (dose) were found to be greatest for specialists, followed by maintenance workers, generalists, bystanders, and DIY. On a comparative basis, modeled dose and thus risk from dropped ceilings for all work categories were orders of magnitude lower than published exposures for other sources of banned friable asbestos‐containing building material commonly encountered in construction trades.     

Social Norms and Motivations Associated with College Binge Drinking*

This study proposes that members of Greek social organizations have higher rates of binge drinking as compared to other college students because of their unique social organization, which supports binge drinking. Using data from the College Alcohol Study, logistic regression analysis results show that Greek members binge drink at higher levels than do other students, which supports previous literature ( Cashin, Presley, and Meilman 1998 ). The results also indicate, however, that social norms and motives for drinking which were thought to be predictive of binge drinking practices for all students are actually better predictors of binge drinking for non‐Greek members.     

Observational Stance as a Predictor of Subjective and Genital Sexual Arousal in Men and Women

Observational stance refers to the perspective a person takes while viewing a sexual stimulus, either as a passive observer (observer stance) or an active participant (participant stance). The objective of the current study was to examine the relationship between observational stance and sexual arousal (subjective and genital) across a range of sexual stimuli that do or do not correspond with a participant's sexual attraction (preferred or nonpreferred stimuli, respectively). Regression analyses revealed that, for men (n = 44), participant stance significantly predicted subjective and genital arousal. Women's (n = 47) observer and participant stance predicted subjective arousal but not genital arousal. Analysis of variance showed that participant stance was greatest under preferred sexual stimuli conditions for all groups of participants, while observer stance scores revealed a less consistent pattern of response. This was particularly true for opposite-sex-attracted women, whose ratings of observer stance were lowest for preferred stimuli. Observational stance does not appear to account for gender differences in specificity of sexual arousal; for men, however, participant stance uniquely predicted genital response after controlling for sexual attractions. Similarities in the relationships between men's and women's observational stance and sexual responses challenge previous claims of gender differences in how men and women view erotica.     

Physiological Responses to Near-Miss Outcomes and Personal Control During Simulated Gambling

Near-miss outcomes during gambling are non-win outcomes that fall close to a pay-out. While objectively equivalent to an outright miss, near-misses motivate ongoing play and may therefore be implicated in the development of disordered gambling. Given naturalistic data showing increases in heart rate (HR) and electrodermal activity (EDA) during periods of real gambling play, we sought to explore the phasic impact of win, near-miss and full-miss outcomes on physiological arousal in a controlled laboratory environment. EDA and HR were monitored as healthy, student participants (n = 33) played a simulated slot-machine task involving unpredictable monetary wins. A second gambling distortion, perceived personal control, was manipulated within the same task by allowing the participant to select the play icon on some trials, and having the computer automatically select the play icon on other trials. Near-misses were rated as less pleasant than full-misses. However, on trials that involved personal choice, near-misses produced higher ratings of ‘continue to play’ than full-misses. Winning outcomes were associated with phasic EDA responses that did not vary with personal choice. Compared to full-misses, near-miss outcomes also elicited an EDA increase, which was greater on personal choice trials. Near-misses were also associated with greater HR acceleration than other outcomes. Near-miss outcomes are capable of eliciting phasic changes in physiological arousal consistent with a state of subjective excitement, despite their objective non-win status.     

Accounting for Uncertainty in Heteroscedasticity in Nonlinear Regression

Toxicologists and pharmacologists often describe toxicity of a chemical using parameters of a nonlinear regression model. Thus estimation of parameters of a nonlinear regression model is an important problem. The estimates of the parameters and their uncertainty estimates depend upon the underlying error variance structure in the model. Typically, a priori the researcher would not know if the error variances are homoscedastic (i.e., constant across dose) or if they are heteroscedastic (i.e., the variance is a function of dose). Motivated by this concern, in this paper we introduce an estimation procedure based on preliminary test which selects an appropriate estimation procedure accounting for the underlying error variance structure. Since outliers and influential observations are common in toxicological data, the proposed methodology uses M-estimators. The asymptotic properties of the preliminary test estimator are investigated; in particular its asymptotic covariance matrix is derived. The performance of the proposed estimator is compared with several standard estimators using simulation studies. The proposed methodology is also illustrated using a data set obtained from the National Toxicology Program.