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.     

The influence of religiosity on charitable behavior: A COPPS investigation

We examine the role of religion in charitable giving and find that the religious preference of both the donor and the recipient organization influence giving behavior. By exploiting a panel survey of charitable giving, we demonstrate that traditional empirical analysis on charitable giving masks important differences among donor groups. Religious giving by religious individuals is least responsive to changes in price and income, while secular giving by secular individuals has the greatest sensitivity.     

Point Estimates of Test Sensitivity and Specificity from Sample Means and Variances

In a wide variety of biomedical and clinical research studies, sample statistics from diagnostic marker measurements are presented as a means of distinguishing between two populations, such as with and without disease. Intuitively, a larger difference between the mean values of a marker for the two populations, and a smaller spread of values within each population, should lead to more reliable classification rules based on this marker. We formalize this intuitive notion by deriving practical, new, closed-form expressions for the sensitivity and specificity of three different discriminant tests defined in terms of the sample means and standard deviations of diagnostic marker measurements. The three discriminant tests evaluated are based, respectively, on the Euclidean distance and the Mahalanobis distance between means, and a likelihood ratio analysis. Expressions for the effects of measurement error are also presented. Our final expressions assume that the diagnostic markers follow independent normal distributions for the two populations, although it will be clear that other known distributions may be similarly analyzed. We then discuss applications drawn from the medical literature, although the formalism is clearly not restricted to that application.     

Longitudinal Links between Adolescent and Peer Conduct Problems and Moderation by a Sensitivity Genetic Index

The most extensively studied influence on adolescent conduct problem behaviors is peers, and the literature points to genetics as one source of individual differences in peer influence. The purpose of this study was to test the hypothesis that an environmental sensitivity genetic index comprised of DRD4, 5‐HTTLPR, and GABRA2 variation would moderate the association between peer and adolescent conduct problems. Latent growth modeling was applied to PROSPER project longitudinal data from adolescents and their peers. Results showed the hypothesis was supported; adolescents with more copies of putative sensitivity alleles were more strongly influenced by their peers. The interaction form was consistent with differential susceptibility in follow‐up analyses. Strengths and weaknesses of genetic aggregates for sensitivity research are discussed.     

Racial diversity in the suburbs: how race-neutral responses to demographic change perpetuate inequity in suburban school districts

Suburbs across the US are experiencing dramatic demographic shifts, yet there is little research available on how suburban school districts are dealing with these changes. In this article, we examine the discourses surrounding race and demographic change in three suburban school districts that have been undergoing rapid demographic changes and which contain demographically distinct areas within their district boundaries. Utilizing a critical discourse analysis (CDA) approach, we analyze how the policy context (federal and state) frames actors’ discourses and understandings of race, paying particular attention to the political and institutional factors affecting school policy. We illustrate how the discourse, in turn, is related to the actions (or inactions) taken by district and school leaders to respond to demographic change. We conclude the article by discussing policy implications and potential challenges districts may face in the future if efforts to purposively address racial changes continue to be avoided.     

Demand for gambling: development and assessment of a gambling purchase task

Self-report purchase tasks are a novel approach examining the reinforcing value of addictive behaviour relative to increasing monetary costs required to access the addictive behaviour (i.e. demand). These measures reveal a positive relationship between the indices of demand and addiction problem severity and can elucidate factors associated with motivation for substance use. Gambling is an addictive behaviour that has not been examined using this paradigm. This study seeks to adapt and examine the purchase task for gambling behaviour. A gambling purchase task was devised that asked individuals how often per month they would gamble at various cover charges. Participants were 73 adults from the community with either gambling disorder (n = 28) or alcohol use disorder (n = 24) or were a healthy control (n = 21). Both the alcohol and gambling purchase tasks were administered. Results demonstrate discriminant validity of the gambling purchase task, as individuals with gambling disorder have significantly greater demand for accessing gambling than other groups. The alcohol purchase task also evidenced discriminant validity in that individuals with alcohol use disorder have significantly greater demand for alcohol than other groups. These findings support the use of the gambling purchase task to assess the demand for gambling.     

Gambling-related problems across life domains: an exploratory study of non-treatment-seeking weekly gamblers

This study uses content analysis to provide a qualitative exploration of how life roles are affected by frequent (i.e. at least weekly) gambling, based on in-depth interviews with a community sample of 161 non-treatment-seeking frequent gamblers. Over half (51.6%) of the participants indicated problems associated with gambling and 131 examples were identified. The majority of problems were relational (50.4%), followed by financial (19.8%), work (13.7%), and school related (8.4%). Slightly less than half of participants (41.7%) reported losses due to gambling and 92 examples were provided. The most frequently reported loss was identity related (54.3%), which included self-esteem/shame (38.0%), estrangement from family (34.0%), estrangement from friends (16.0%), and estrangement from work colleagues (6.0%). Additional losses included health (29.3%) and financial (8.7%). Almost two-thirds of participants (64.6%) reported difficulty concentrating in family (18.4%), work (16.8%), and school (9.6%) activities, whereas general concentration problems comprised an additional 48.8% of the examples provided. Half of participants (49.1%) discussed behavioral withdrawal due to gambling, which included withdrawal from work (44.3%), relationships (24.5%), school (15.1%), and personal (6.6%) activities. These findings paint a complex picture of how gambling interferes with different life roles for some frequent gamblers, identifying important areas for future research and practice.