Variance estimation in complex survey sampling for generalized linear models

Summary.  Complex survey sampling is often used to sample a fraction of a large finite population. In general, the survey is conducted so that each unit (e.g. subject) in the sample has a different probability of being selected into the sample. For generalizability of the sample to the population, both the design and the probability of being selected into the sample must be incorporated in the analysis. In this paper we focus on non-standard regression models for complex survey data. In our motivating example, which is based on data from the Medical Expenditure Panel Survey, the outcome variable is the subject's 'total health care expenditures in the year 2002'. Previous analyses of medical cost data suggest that the variance is approximately equal to the mean raised to the power of 1.5, which is a non-standard variance function. Currently, the regression parameters for this model cannot be easily estimated in standard statistical software packages. We propose a simple two-step method to obtain consistent regression parameter and variance estimates; the method proposed can be implemented within any standard sample survey package. The approach is applicable to complex sample surveys with any number of stages.     

Inside the Locker Room: Male Homosociability in the Advertising Industry

The use of the term homosociability by male employers and employees has been a key issue in the construction and maintenance of the gendered labour market, especially in senior‐level jobs. Male homosociability encompasses the formal old boys' networks and informal clubs or meetings, as well as humour and banter, referred to metaphorically in this article as the locker room. This article examines the locker room and its resulting forms of socializing, socialization, communication and rituals found in the advertising industry. To gain a clearer understanding of how the locker room constructs workplace opportunities, this article draws upon qualitative research and analysis and examines major service occupations in the advertising industry and the executives who inhabit them. Studying the relationship between the locker room and the production process provides additional perspectives on service work in the corporate sector, occupations and gender inequality.     

Social Movements and Collective Memory

This article summarizes key findings and provides suggestions for further research in the literature that combines social movements and collective memory. Existing reviews of the collective memory literature highlight the macro and micro levels of analysis; studying movements and memory adds a meso level of analysis. This review covers all three levels and for each level discusses research methods, the social consequences of memory activism, recurring patterns, and explanations. Suggestions for future research emphasize the concept of repertoire and its relation to memory. Tactical repertoires and cultural repertoires provide the resources needed to construct collective memories, and repertoires empower memory activists to engage the political sphere, create change, and nurture solidarity within movement organizations. Because the idea of a repertoire uncovers a process of remembering and is already a widely used term in social movement studies, it provides a resonant tool for future movement and memory research.     

Media Exposure and Health in Europe: Mediators and Moderators of Media Systems

This study examined media exposure as an explanatory factor for individual and cross-national differences in self-assessed general health. In studying media exposure, traditional media (television, radio, and newspapers) and contemporary media (internet) were separately considered. Aside from hypotheses about the relation between media exposure and general health, we also tested hypotheses regarding the mediating role of social isolation and mean world syndrome as well as the moderating role of different media systems across countries. Therefore, we used European Social Survey 2010, covering 25 European countries (n = 36,692). The results of our multilevel regression analyses indicated that exposure to television was negatively related to general health, whereas exposure to radio and newspapers were positively related to health. For contemporary media, findings indicated consistent positive relations between internet exposure and health across. Furthermore, limited support was found for the mediating role of social isolation and the mean world syndrome in the link between media exposure and health. Across media systems, findings for the relations between exposure to the various types of media and health proved to be robust.     

Experiences and Perceptions of Problem Gamblers on Cognitive and Exposure Therapies When Taking Part in a Randomised Controlled Trial: A Qualitative Study

In South Australia (SA) problem gambling is mainly a result of the widespread availability of electronic gaming machines. A key treatment provider in SA offers free cognitive and behavioural therapy (CBT) to help-seeking problem gamblers. The CBT program focuses on the treatment of clients’ urge to gamble using exposure therapy (ET) and cognitive therapy (CT) to restructure erroneous gambling beliefs. The aim of this study was to explore treatment specific and non-specific effects for CT alone and ET alone using qualitative interviews. Interviewees were a sub-sample of participants from a randomised trial that investigated the relative efficacy of CT versus ET. Findings revealed that all interviewees gained benefit from their respective therapies and their comments did not appear to favour one therapy over another. Both treatment specific and treatment non-specific effects were well supported as playing a therapeutic role to recovery. Participants’ comments in both therapy groups suggested that symptom reduction was experienced on a gambling related urge–cognition continuum. In addition to symptom improvement from therapy-specific mechanisms, ET participants described a general acquisition of “rational thought” from their program of therapy and CT participants had “taken-over” their gambling urges. The findings also highlighted areas for further improvement including therapy drop-out.     

Exposure Therapy for Problem Gambling via Videoconferencing: A Case Report

This case report of a 31 year old woman who described her main problem as an uncontrollable urge to gamble on electronic gaming machines describes the application of exposure therapy (ET) by videoconferencing and the use of a clinical therapy assistant in the treatment of pathological gambling. The case study is used to demonstrate the effectiveness of this treatment with six sessions of therapy and 4 year follow up. The use of videoconferencing is discussed in relation to treatment effectiveness, ongoing follow up for the client and education and support for a community mental health nurse, therapy assistant, in a rural setting in South Australia. The implications of using this modality for the treatment of rural patients with problem gambling is discussed.     

Machine Learning Methods as a Tool for Predicting Risk of Illness Applying Next‐Generation Sequencing Data

Next‐generation sequencing (NGS) data present an untapped potential to improve microbial risk assessment (MRA) through increased specificity and redefinition of the hazard. Most of the MRA models do not account for differences in survivability and virulence among strains. The potential of machine learning algorithms for predicting the risk/health burden at the population level while inputting large and complex NGS data was explored with Listeria monocytogenes as a case study. Listeria data consisted of a percentage similarity matrix from genome assemblies of 38 and 207 strains of clinical and food origin, respectively. Basic Local Alignment (BLAST) was used to align the assemblies against a database of 136 virulence and stress resistance genes. The outcome variable was frequency of illness, which is the percentage of reported cases associated with each strain. These frequency data were discretized into seven ordinal outcome categories and used for supervised machine learning and model selection from five ensemble algorithms. There was no significant difference in accuracy between the models, and support vector machine with linear kernel was chosen for further inference (accuracy of 89% [95% CI: 68%, 97%]). The virulence genes FAM002725, FAM002728, FAM002729, InlF, InlJ, Inlk, IisY, IisD, IisX, IisH, IisB, lmo2026, and FAM003296 were important predictors of higher frequency of illness. InlF was uniquely truncated in the sequence type 121 strains. Most important risk predictor genes occurred at highest prevalence among strains from ready‐to‐eat, dairy, and composite foods. We foresee that the findings and approaches described offer the potential for rethinking the current approaches in MRA.     

Racial Diversity,Representative Bureaucracy,and Equity in Multiracial School Districts*

Objective. This study examines the conditions under which minorities will face policy inequity within the educational system. It turns to the theory of representative bureaucracy as one possible explanation, and extends the literature by considering whether African‐American students benefit from the presence of Latinos on teaching faculties and vice versa. This study also tests competing theories of how racial context influences minority educational policy outcomes. Methods. This study combines original survey data with data gathered by the U.S. Census to predict levels of academic grouping in U.S. school districts as reported by the Office of Civil Rights. Results. Minority teachers lower levels of discrimination among all minority students, not just co‐ethnics. Moreover, minority teachers do so consistently and with a substantive impact that occasionally rivals that of co‐ethnic teachers. The findings also suggest that greater levels of racial/ethnic diversity within a district are associated with lower levels of discrimination. Conclusion. Theories of race relations must move beyond black‐Anglo or Latino‐Anglo relations to consider how multiple racial/ethnic groups interact, and how such interactions affect the lives of minority groups differently.