Two-sample tests for sparse high-dimensional binary data

In this article, we study the methods for two-sample hypothesis testing of high-dimensional data coming from a multivariate binary distribution. We test the random projection method and apply an Edgeworth expansion for improvement. Additionally, we propose new statistics which are especially useful for sparse data. We compare the performance of these tests in various scenarios through simulations run in a parallel computing environment. Additionally, we apply these tests to the 20 Newsgroup data showing that our proposed tests have considerably higher power than the others for differentiating groups of news articles with different topics.     

Intimate Partner Violence: Modifying an Internet-Based Safety Decision Aid to a New Zealand Context

Women experiencing intimate partner violence face complex decisions in navigating their safety. In a feasibility study, we examined the suitability of an intimate partner violence interactive online decision aid developed in the United States for its application in New Zealand, particularly with regard to cultural appropriateness. We conducted focus group sessions with women who experienced partner violence and focus group sessions with service providers. Women completed the U.S. online decision aid tool and provided feedback on the safety decision criteria, content, and design. Considering the findings from the focus group sessions the decision aid was modified. We reflect on the process of balancing women's stories with technical limitations and constraints of a replication study.     

The Effects of Expectation Disconfirmation on Appraisal,Affect, and Behavioral Intentions

People's risk perceptions can have powerful effects on their outcomes, yet little is known about how people respond to risk information that disconfirms a prior expectation. We experimentally examined the affective, cognitive, and behavioral consequences of expectation disconfirmation in the context of risk perceptions. Participants were randomly assigned and then prompted toward either a high or low personal risk estimate regarding a fictitious health threat. All participants then received the same risk feedback, which presented either a negative disconfirmation experience (i.e., worse than expected) in the high‐risk estimate condition or a positive disconfirmation experience (i.e., better than expected) in the low‐risk estimate condition. Participants who experienced the negative disconfirmation reported stronger intentions to prevent the threat in the future compared to participants who experienced the positive disconfirmation. This effect was mediated by both disappointment about the risk feedback and perceptions of the severity of the threat. These findings have implications for risk communication, suggesting that the provision of objective risk information may improve or diminish the likelihood of behavior change depending on people's initial expectations and their emotional and cognitive reactions to the information.     

Religion and New Media: A Uses and Gratifications Approach

This research examines specific relationships between new media and religion. While prior research has focused on the question of whether a relationship exists, we explore technology usage as a predictor of specific religious behavior. Using a sample (N = 423) comprising a cross-section of religious and cultural backgrounds, results indicate that attitudes toward technology and use of social media contribute to how people view religion as a mechanism for meeting needs. Applying uses and gratifications theory in a unique way, three needs related to religion emerged: religion as a means of passing time, religion as a mode of meeting self needs, and religion as a catalyst for learning. We discuss implications of our findings.     

A Model of Engagement Promotion in a Professionally Facilitated Online Intervention for Couples Affected by Breast Cancer

Professionally facilitated web‐based interventions for couples affected by an illness such as cancer are growing in popularity. Attrition rates for such online programs, however, are substantially higher than what is observed in face‐to‐face therapeutic contexts, and lower levels of participant engagement are associated with poorer outcomes. In the present investigation, a task analysis was employed to develop a model of engagement promotion in an online intervention for couples affected by breast cancer called “Couplelinks.” Results indicated that facilitators utilized a variety of meta‐processes, such as humanizing the technology, and associated “eBehaviors,” to maintain three relationships involved in promoting online engagement: (a) between the facilitator and couple; (b) between the intervention and couple; and (c) between the partners within the couple.     

Characteristics of Communication in Families of Alcoholics

In the United States, roughly 43% of adults have encountered alcoholism in their family, and one in four children lives with an alcoholic parent (Grant, 2000). Prior research suggests that alcoholism can negatively impact the nature and quality of family relations, but studies rarely consider the specific ways in which family communication dynamics are impacted by the disease. Thus, the goal of this study was to identify the characteristics of communication in families of alcoholics and to develop a larger conceptual model to guide future inquiries in this context. A national sample of 682 adult children of alcoholics were asked to describe the communication dynamics in their family of origin. A theme analysis of the open-ended data revealed four overarching themes that were comprised of nine subcategories: (a) aggressive communication (e.g., heightened conflict, tense communication, and secretive slandering); (b) protective communication (e.g., superficiality, limited or indirect communication, and sober parent buffering); (c) adaptive communication (e.g., functional communication); and, (d) inconsistent communication (e.g., struggles over power and control, mood fluctuation). We draw on the results of this analysis to propose a model depicting communication dynamics in families of alcoholics and the antecedent conditions and consequent outcomes of such communication patterns in the family.     

A Shorter and Multidimensional Version of the Gambling Attitudes and Beliefs Survey (GABS-23)

The Gambling Attitudes and Beliefs Survey (GABS) is a questionnaire which explores gambling-related dysfunctional beliefs in an unidimensional way. The present research aims to investigate the dimensionality of the scale. 343 undergraduate student gamblers and 75 pathological gamblers seeking treatment completed the GABS and the south oaks gambling screen. Exploratory and confirmatory factor analyses revealed that the original one-factor structure of the GABS did not fit the data effectively. We then proposed a shorter version of the GABS (GABS-23) with a new five-factor structure, which fitted with the data more efficiently. The comparisons between students (problem vs. non-problem gamblers) and pathological gamblers seeking treatment indicated that the GABS-23 can discriminate between problem and non-problem gamblers as efficiently as the original GABS. To ensure the validity and the stability of the new structure of the GABS-23, analyses were replicated in an independent sample that consisted of 628 gamblers (256 non problem gamblers, 169 problem gamblers who are not treatment-seeking and 203 problem gamblers seeking treatment). Analyses showed satisfactory results, and the multidimensional structure of the GABS-23 was then confirmed. The GABS-23 seems to be a valid and useful assessment tool for screening gambling-related beliefs, emotions and attitudes among problem and non-problem gamblers. Moreover, it presents the advantage of being shorter than the original GABS, and of screening irrational beliefs and attitudes about gambling in a multidimensional way. The five-factor model of the GABS-23 is discussed based on the theory of locus of control.     

Occupational health and safety issues affecting young workers: a literature review

Many overview articles, reports, book chapters and literature reviews have examined the health and safety of young workers. These sources discuss the relationships between the work conditions of young workers and the various indicators of accidents and occupational diseases. Breslin et al. [12,13] conducted two literature reviews of quantitative studies to determine which factors best predicted work accidents and occupational disorders in young people. The present article proposes a review of young people's occupational health and safety (OHS) factors (e.g., demographic, individual, professional, organizational, temporal and operational factors) in both qualitative and quantitative studies. Five types of problems were analyzed in greater depth, namely MSD symptoms, respiratory, allergy and toxicological problems, mental health and well-being, alcohol and drug consumption, and fatigue. This review likewise examines related dimensions that allow us to adopt a more global perspective on this subject by considering such elements as young people's values, their knowledge and attitudes, safety practices in companies, the safe integration of young people, and rehabilitation. A total of 189 scientific articles were selected on the basis of certain criteria. These articles came from refereed OHS journals published between 1994 and 2005.