The effects of covariate adjustment in generalized linear models

Results from classical linear regression regarding the effects of covariate adjustment, with respect to the issues of confounding, the precision with which an exposure effect can be estimated, and the efficiency of hypothesis tests for no treatment effect in randomized experiments, are often assumed to apply more generally to other types of regression models. In this paper results pertaining to several generalized linear models involving a dichotomous response variable are given, demonstrating that with respect to the issues of confounding and precision, for models having a linear or log link function the results of classical linear regression do generally apply, whereas for other models, including those having a logit, probit, log-log, complementary log-log, or generalized logistic link function, the results of classical linear regression do not always apply. It is also shown, however, that for any link function, covariate adjustment results in improved efficiency of hypothesis tests for no treatment effect in randomized experiments, and hence that the classical linear regression results regarding efficiency do apply for all models having a dichotomous response variable.     

A Trivariate Distribution for the Height,Weight, and Fat of Adult Men*

Using exploratory data analysis, probability plots, scatterplots, and computer animations to rotate and visualize the data, we fit a trivariate Normal distribution to data for the height, the natural logarithm of body weight, and the body fat for 646 men between the ages of 50 and 80 years as reported by the medical staff of the U.S. Veterans Administration's “Normative Aging Study” in Boston, MA. Although these data do not include any children, women, or young men, the measurements represent the best data that we could find through a 4-year search. We believe that these data are well measured and reliable for men in the specified age range and that these data reveal an interesting statistical pattern for use in probabilistic PBPK models.     

Academic Entrepreneurship: Time for a Rethink?

Academic entrepreneurship, which refers to efforts undertaken by universities to promote commercialization on campus and in surrounding regions of the university, has changed dramatically in recent years. Two key consequences of this change are that more stakeholders have become involved in academic entrepreneurship and that universities have become more ‘strategic’ in their approach to this activity. The authors assert that the time is ripe to rethink academic entrepreneurship. Specifically, theoretical and empirical research on academic entrepreneurship needs to take account of these changes, so as to improve the rigour and relevance of future studies on this topic. We outline such a framework and provide examples of key research questions that need to be addressed to broaden understanding of academic entrepreneurship.     

Relationship of interpersonal behaviors and health-related control appraisals to patient satisfaction and compliance in a university health center

OBJECTIVE: The authors' aim was to evaluate patient-provider relationships in a college health center. PARTICIPANTS: Eighty student patients and their health-care providers. METHODS: Patients completed a measure of perceived health competence before a consultation and measures of provider participatory behavior and interpersonal behavior before and after the consultation. They evaluated their satisfaction with care and compliance after the consultation and again 2 weeks later. Providers completed measures of their participatory behavior and patients' interpersonal behavior after the consultation. RESULTS: Patients preferred to be well informed and to have their preferences taken into account, and generally felt competent at managing their own health affairs. They indicated they obtained the high level of participation they desired. Patients desired and actually experienced friendly and submissive providers. Degree of match between patients' desired and actual level of involvement in their care was associated with greater satisfaction. A greater match between the extent to which they desired the provider to be affiliative and the provider's actual affiliative behavior was associated with more satisfaction. No variables were predictive of patient compliance. CONCLUSION: The authors discuss results in terms of the influence of situational factors characteristic of a college health center.     

The self-perceptions and interpersonal relationships of persons with significant physical disabilities: a qualitative pilot study

This exploratory, qualitative research was conducted to obtain the perspectives of people with significant physical disabilities regarding factors that have facilitated and hindered the development of a positive self-concept, participation in the broader society, and the formation of interpersonal relationships. The sample was high achieving in terms of education and/or career and attributed positive self-perceptions and their success in the broader society and interpersonal relationships to the attitudes and perceptions regarding their abilities, talents, and potential modeled in supportive family relationships. Females reported the influence of significant others most often, and males the effectiveness of their personality characteristics. Societal barriers, both practical and attitudinal, were reported along with the process for developing a positive selfperception despite these.     

A Stochastic Goal Program for Employee Scheduling*

Deterministic goal programs for employee scheduling decisions attempt to minimize expected operating costs by assigning the ideal number of employees to each feasible schedule. For each period in the planning horizon, managers must first determine the amount of labor that should be scheduled for duty. These requirements are often established with marginal analysis techniques, which use estimates for incremental labor costs and shortage expenses. Typically, each period in the planning horizon is evaluated as an independent epoch. An implicit assumption is that individual employees can be assigned to schedules with as little as a single period of work. If this assumption violates local work rules, the labor requirements parameters for the deterministic goal program may be suboptimal. As we show in this research, this well-known limitation can lead to costly staffing and scheduling errors. We propose an employee scheduling model that overcomes this limitation by integrating the labor requirements and scheduling decisions. Instead of a single, externally determined staffing goal for each period, the model uses a probability distribution for the quantity of labor required. The model is free to choose an appropriate staffing level for each period, eliminating the need for a separate goal-setting procedure. In most cases this results in better, less costly decisions. In addition, the proposed model easily accommodates both linear and nonlinear under- and overstaffing penalties. We use simple examples to demonstrate many of these advantages and to illustrate the key techniques necessary to implement our model. We also assess its performance in a study of more than 1,700 simulated stochastic employee scheduling problems.     

Relationship of bird richness,abundance and assemblage to the built environment in a small island tropical urban setting: a Suva,Fiji case study

There have been few studies investigating the relationship between the built environment and the status of bird distributions in small island tropical urban areas. We present a study investigating the relationship between bird species richness, abundance and assemblage to the built environment in Suva, Fiji. Field surveys were taken at 54 randomly selected sites throughout the city, stratified by three building density classes and the central business district (CBD). At each site bird counts were recorded, along with environmental data such as average building height, within a 150 m radius. Land-use information was obtained from screen digitized high-resolution satellite imagery within the same radius. Distance to undeveloped patches of land within the urban area was calculated using a GIS. Analysis of the effects of the built environment was carried out for all species, and for exotic and native species separately. Abundance of exotics was significantly higher in the central business district (CBD) than all other urban density classes, and significantly higher than natives in all other density classes. We found a negative relationship between native species richness and distance to undeveloped patches, but no relationship for exotics. Species assemblage was not related to urban density class. We conclude that the status of native and exotic bird species in Suva is similar to what has been found in urban areas in temperate climates, and conservation efforts should focus on minimizing the amount of heavily urbanized “core areas” and protecting undeveloped areas of forested vegetation to improve bird biodiversity in small tropical islands cities.

     

Some indications of limits to framing the policy preferences of the civically engaged: Interplay of social capital,race attitudes,and social justice frames

Our experiment, which tested support for a hypothetical social welfare program, found that the civically engaged as a whole were resistant to social justice framing employing universalistic versus particularistic standards. We suggest the lack of a framing effect was due to the use of a preexisting, shared “symbolic racism” frame. Social justice framing did succeed for those whose attitudes toward symbolic racism were ambivalent or neutral. Other factors including sex, income level, political participation, and ideology significantly influenced choice. These results provide some indications of limits to experimental framing of policy preferences of the civically engaged in their institutional settings.     

MARKET STRUCTURE AND MEDIA DIVERSITY

We estimate a mixed logit model of the demand for local news service. Results provide evidence that suggest the representative consumer values more diverse news, more coverage of multicultural issues, and more information on community news, and has a distaste for advertising. Demand estimates are used to calculate the impact on consumer welfare from a marginal decrease in the number of independent television stations that lowers the amount of diversity, multiculturalism, community news, and advertising. Consumer welfare decreases, but the losses are smaller in large markets. For example, small‐market consumers lose $45 million annually while large‐market consumers lose $13 million. (JEL C9, C25, L13, L82, L96)