Disaggregated spatial modelling for areal unit categorical data

Summary.  We consider joint spatial modelling of areal multivariate categorical data assuming a multiway contingency table for the variables, modelled by using a log-linear model, and connected across units by using spatial random effects. With no distinction regarding whether variables are response or explanatory, we do not limit inference to conditional probabilities, as in customary spatial logistic regression. With joint probabilities we can calculate arbitrary marginal and conditional probabilities without having to refit models to investigate different hypotheses. Flexible aggregation allows us to investigate subgroups of interest; flexible conditioning enables not only the study of outcomes given risk factors but also retrospective study of risk factors given outcomes. A benefit of joint spatial modelling is the opportunity to reveal disparities in health in a richer fashion, e.g. across space for any particular group of cells, across groups of cells at a particular location, and, hence, potential space–group interaction. We illustrate with an analysis of birth records for the state of North Carolina and compare with spatial logistic regression.     

Teaching Sociological Practice: Starting with Something Special

A scholar-practitioner might want to decide what concept, value, or framework in sociological practice is particularly important for students to know at the very beginning of a course. This special emphasis approach is detailed using four examples: cultural competence in a course on mediation skills; humanism in courses or presentations on social theory, ethics, social planning, or intervention; participatory action research in a social science research course; and empowerment in intervention, community, social planning, or social policy courses. Clinical and applied sociologists are invited to consider an up front and personal approach in at least some of their courses and to choose and explicitly emphasize, in their own special way, an important value, concept, or perspective at the beginning of a course.     

Sex differences in morbidity and mortality

Women have worse self-rated health and more hospitalization episodes than men from early adolescence to late middle age, but are less likely to die at each age. We use 14 years of data from the U.S. National Health Interview Survey to examine this paradox. Our results indicate that the difference in self-assessed health between women and men can be entirely explained by differences in the distribution of the chronic conditions they face. This is not true, however, for hospital episodes and mortality. Men with several smoking-related conditions--including cardiovascular disease and certain lung disorders--are more likely to experience hospital episodes and to die than women who suffer from the same chronic conditions, implying that men may experience more-severe forms of these conditions. While some of the difference in mortality can be explained by differences in the distribution of chronic conditions, an equally large share can be attributed to the larger adverse effects of these conditions on male mortality. The greater effects of smoking-related conditions on men's health may be due to their higher rates of smoking throughout their lives.     

Promoting Transparency of Long-Term Environmental Decisions: The Hanford Decision Mapping System Pilot Project

Nuclear waste cleanup is a challenging and complex problem that requires both scientific analysis and dialogue among a variety of stakeholders. This article describes an effort to develop an online information system that supports this analytic-deliberative dialogue by integrating cleanup information for the Hanford Site, and making it more "transparent." A framework for understanding and evaluating transparency guided system development. Working directly with stakeholders, we identified information needs and developed new ways to organize and present the information so that it would be more transparent to interested parties, with the ultimate aim of fostering greater participation in decision dialogues and processes. The complexity of the information needed for dialogue suggested that several types of communication devices ("information structures") were warranted. Five information structures were developed for the pilot Decision Mapping System (http://nalu.geog.washington.edu/dms). Decision maps hyperlinked decision information to maps of Hanford. Background Information provided context in a narrative format. Decision Paths organized decision process information on a timeline and provided direct hyperlinks to online documentation. The Geographic Library hyperlinked decision documents to maps. Finally, a Discussion Forum allowed users to make comments and view remarks from others. Early lessons from this work suggest that transparency is integral to long-term management, a participatory design process contributed greatly to its perceived success, and better data integration to support decision making is needed. This work has broad implications for risk communicators and risk managers because it speaks to the design of information systems to support "analytic-deliberative" decision processes (i.e., those that rely upon both risk science and public dialogue).     

My student body: a high-risk drinking prevention web site for college students

The authors investigated the efficacy of an interactive Web site, MyStudentBody.com: Alcohol (MSB:Alcohol) that offers a brief, tailored intervention to help heavy drinking college students reduce their alcohol use. They conducted a randomized, controlled clinical trial to compare the intervention with an alcohol education Web site at baseline, postintervention, and 3-month follow-up. Students were assessed on various drinking measures and their readiness to change their drinking habits. The intervention was especially effective for women and persistent binge drinkers. Compared with women who used the control Web site, women who used the intervention significantly reduced their peak and total consumption during special occasions and also reported significantly fewer negative consequences related to drinking. In addition, persistent heavy binge drinkers in the experimental group experienced a more rapid decrease in average consumption and peak consumption compared with those in the control group. The authors judged MSB:Alcohol a useful intervention for reaching important subgroups of college binge drinkers.     

Environment and sex ratios among Alaska Natives: An historical perspective

Human-environment interactions can affect the sex ratios of resource-dependent societies in a variety of ways. Historical and contemporary data on Alaska Native populations illustrate such effects. Some eighteenth and early nineteenth century observers noted an excess of females, which they attributed to high mortality among hunters. Population counts in the later nineteenth century and well into the twentieth found instead an excess of men in many communities. Female infanticide was credited as the explanation: since family survival depended upon hunting success, males were more valued. Although infanticide explanations for the excess of males have been widely believed, available demographic data point to something else: higher adult female mortality. Finally, in the postwar years, the importance of mortality differentials seems to have faded- and also changed direction. Female outmigration from villages accounts for much of the gender imbalance among Native populations today. Natural-resource development, particularly North Slope oil, indirectly drives this migration. In Alaska's transcultural communities, the present gender imbalances raise issues of individual and cultural survival.     

Private lives,public accountability: A case study

Lend a Hand Children's Services is the most prominent provider of family services in rural south central Ohio. The agency is in the process of enlarging its fundraising goals and becoming even bigger in the community. Staff have brought to the attention of the vice president of the board that the board president and the executive director may be involved intimately as a couple. Inasmuch as the board president must evaluate the executive director, the vice president turns to trusted counsel for advice on how to approach the unique problems raised by the situation.