Hypothesis Tests for Neyman's Bias in Case–Control Studies

Survival bias is a long recognized problem in case–control studies, and many varieties of bias can come under this umbrella term. We focus on one of them, termed Neyman's bias or ‘prevalence–incidence bias’. It occurs in case–control studies when exposure affects both disease and disease-induced mortality, and we give a formula for the observed, biased odds ratio under such conditions. We compare our result with previous investigations into this phenomenon and consider models under which this bias may or may not be important. Finally, we propose three hypothesis tests to identify when Neyman's bias may be present in case–control studies. We apply these tests to three data sets, one of stroke mortality, another of brain tumors, and the last of atrial fibrillation, and find some evidence of Neyman's bias in the former two cases, but not the last case.     

Teaching Business Demography Using Case Studies

Many faculty members consider using case studies but not all end up using them. We provide a brief review of what cases are intended to do and identify three ways in which they can be used. We then use an example to illustrate how we have used the case study method in teaching business demography. Among other benefits, we note that the case studies method not only encourages the acquisition of skills by students, but can be used to promote “deep structure learning,” an approach naturally accommodates other features associated with the case studies method—the development of critical thinking skills, the use of real world problems, the emphasis of concepts over mechanics, writing and presentation skills, active cooperative learning and the “worthwhileness” of a course. As noted by others, we understand the limitations of the case study method. However, given its strengths, we believe it has a place in the instructional toolbox for courses in business demography. The fact that courses we teach is a testament to our perceived efficacy of this tool.     

New Directions in the Development of Population Estimates in the United States?

The advent of a continuously updated Master Area File (MAF) following the 2000 census represents an information resource that can be tapped for purposes of developing timely, cost-effective, and precise population estimates for even the smallest of geographical units (e.g., census blocks). We argue that the MAF can be enhanced (EMAF) for these purposes. In support of our argument we describe a set of activities needed to develop EMAF, each of which is well within the current capabilities of the U.S. Census Bureau and discuss various costs and benefits of each. We also describe how EMAF would provide population estimates containing a wide range of demographic (e.g., age, race, and sex) and socio-economic characteristics (e.g., educational attainment, income, and employment). As such, it could largely negate and eliminate the need for many of the traditional demographic methods of population estimation and possibly reduce the number of sample surveys. We identify important challenges that must be surmounted in order to realize EMAF and make suggestions for doing so. We conclude by noting that the idea of the EMAF could be of interest to other countries with MAF files and strong administrative records systems that, like the United States, are facing the challenge of producing good population information in the face of increasing census costs.     

After a Disaster: Lessons in Survey Methodology from Hurricane Katrina

In 2005, the National Science Foundation funded a number of projects to study the impact of Hurricane Katrina. The current article provides an overview of several research approaches used to conduct post-Katrina research. Each method had some advantages and disadvantages. The post-disaster context meant that experience from traditional survey methods often did not apply. Comparisons of advantages and disadvantages associated with each sampling method serve to inform future post-disaster research and illuminate the limits of classical research methods.     

Identity processes and the positive youth development of African Americans: an explanatory framework

This chapter presents Spencer's phenomenological variant of ecological systems theory, or PVEST (1995), as a conceptual framework for examining positive youth development. Contextual factors affecting racial and gender identity of African American youth are discussed, with the focus on the influence of schools and religious institutions.     

The witch doctor's pharmacist

This article explores the state of, and prospects for, training and development within the South African maritime industry, and is based on a series of in-depth interviews conducted with employers, the principal union, training institutions and regulatory bodies. Findings are that a deeply embedded racial division of labour persists, that there is a serious shortage of employment opportunities, and that training and certification remain fragmented. The article concludes that the quality of training provided is of a high standard, but there is a vital need for a coherent overall policy linking initial training with employment opportunities, ongoing skills development and the promotion of greater equality.     

Whose Risk in Philadelphia? Proximity to Unequally Hazardous Industrial Facilities*

Objective. Few researchers have investigated who lives near the worst polluting facilities. In this study, we test for disparate impact from hazardous industrial and infrastructure facilities on racial/ethnic minorities, the disadvantaged, the working class, and manufacturing workers in the nine‐county Philadelphia MSA. Methods. Hazard Scores for Philadelphia‐area facilities in EPA's Risk‐Screening Environmental Indicators (RSEI) database were calculated and facilities mapped onto Census block group maps. One‐kilometer buffer zones around facilities were created and intersected with Census data on population inside and outside buffers. After correcting for spatial autocorrelation, we tested for relationships between Hazard Scores and characteristics of people near facilities using multivariate regression. Results. Hazard Scores rose along with percents black, Hispanic, disadvantaged, and employed in manufacturing in some (but not all) counties. Conclusions. Among those living near polluting facilities, minorities, the poor, and manufacturing workers lived near the most hazardous, constituting a disparate impact on these groups.     

Validity Of Reported Date of Birth, Salary, and Seniority

This study reveals wide variations in actual vs. reported dateof birth, salary, and seniority. It suggests that invalidityis a specialized phenomenon, and that the direction and magnitudeof inaccurate responses are structurally related to characteristicsof the respondents.     

Still Going: Recent Debates on the Goldschmidt Hypothesis1

Abstract The literature on the Goldschmidt (1978a) hypothesis has passed through distinct stages. This article is a commentary on the present status of the literature and particularly on a recent article by Barnes and Blevins (1992). Our arguments draw in large part from our previous work. Researchers in the 1970s and early 1980s were concerned mainly with replicating Goldschmidt's work. However, these studies had a number of methodological and conceptual limitations that limited closure on the debate. A new generation of research from the mid-1980s onward was premised upon addressing the limitations, including the need to incorporate indicators of nonfarm economic structure, to take spatial or geographic features into account, and to adequately conceptualize farm structure. Barnes and Blevins (1992) disregard these inroads, evident in that their article repeats earlier arguments, offers solutions to problems addressed a decade earlier, and is vulnerable to its own methodological problems. To move inquiry forward, new directions for studies concerned with the broader issues raised by Goldschmidt are suggested.