The Renewal of Population Loss in the Nonmetropolitan Great Plains

Abstract An analysis of population trends in 293 nonmetropolitan Great Plains counties from 1950 to 1990 reveals that the population turnaround of the 1970s has indeed ended. During the 1980s, 84 percent of these nonmetropolitan counties had total population declines, a proportion greater than any other decade studied. A majority of counties had natural population increase, but such increases were offset by net outmigration as 96 percent of the counties had such losses during the 1980s. The influence of the independent variables on population change shifted from decade to decade. The most important variable in producing positive population trends was the ability of the county to attract retirement migrants.     

Closed Sequential and Multistage Inference on Binary Responses With or Without Replacement

Logistic regression is used by practitioners and researchers in many fields, but is undoubtedly used most frequently in medical and biostatistical applications. Maximum likelihood is generally the estimation method of choice, but we show that maximum likelihood can produce very poor results under certain conditions. Specifically, the poor performance of maximum likelihood in the case of rare events is known and we review research on this topic. We primarily examine the performance of maximum likelihood in the presence of near separation, which has apparently not been studied. Exact logistic regression is the logical alternative to maximum likelihood. We offer a comparison of the two methods of estimation.     

Bootstrapping analogs of the one way MANOVA test

Abstract

Analogs of the classical one way MANOVA model have recently been suggested that do not assume that population covariance matrices are equal or that the error vector distribution is known. These tests are based on the sample mean and sample covariance matrix corresponding to each of the p populations. We show how to extend these tests using other measures of location such as the trimmed mean or coordinatewise median. These new bootstrap tests can have some outlier resistance, and can perform better than the tests based on the sample mean if the error vector distribution is heavy tailed.     

On the unbiasedness of iterated gls estimators

We Formulate sufficienct conditions for the existonce of the expectation of iterated generalized expectation of the iterated generalized least squares estimator, which consequently guarantee its unbiasedness, The analysis is applied to the maximum likelihood estimator in the general linear model with normal disturbances, where a set of assumptions ensures convergence of the iteration as well as unbiasedness.     

Are Subsidiaries More Prone to Pollute? New Evidence from the EPA's Toxics Release Inventory*

Objective. Some scholars fear that because firms are no longer liable for the hazardous activities of their subsidiaries, the latter are under less corporate pressure to limit their pollution. However, researchers have yet to examine the environmental performance of subsidiaries. This reflects a more general failure on their part to test the effects different organizations have on pollution. Methods. To begin to remedy this situation, we use data from the EPA's Toxics Release Inventory to determine whether subsidiaries emit pollutants at a higher rate than other facilities in the chemical industry. Results. We find that subsidiaries have significantly higher emission rates than other facilities after controlling for several relevant factors. Conclusions. Results suggest how recent research on the structural determinants of environmental degradation might be advanced by focusing on the effects of specific organizational forms.     

Using Personal Quality Assessment for Selection of Social Work Students

Abstract

The social work profession has long struggled to find fair and effective ways of selecting students into their education programs. A psychometric test battery, gathered together under the title “Personal Qualities Assessment” (PQA) has been developed at the University of Newcastle to identify a range of qualities in aspiring health professionals. Two of its components were used to determine whether there was a relationship between scores obtained by social work students in these tests and scores achieved in an empathic listening and critical review hurdle assessment prior to the first field placement. The results showed that social work students who were moderately empathic, not narcissistic, and moderately libertarian in their moral orientation performed better on the assessment than students who were less empathic, more narcissistic, or extreme in their moral orientation. These results suggest that measurement of these qualities could be useful in selecting the most suitable individuals for social work programs.     

Measles and Rubella on College Campuses: The Need to Act

Abstract

The lack of immunization requirements at the nation's colleges and universities threatens the maintenance of the interruption of indigenous measles in the United States. The high susceptibility rates in some college populations coupled with the high mobility of college students who may travel to countries where measles is endemic or epidemic increases the potential for measles outbreaks.

Preventing measles in college-age populations is particularly important because the disease can be more serious in adults. In view of the importance of preventing measles in college students, the Immunization Practices Advisory Committee (ACIP) of the U.S. Public Health Service has recommended that officials strongly consider immunization requirements for college entry.

The ultimate goal of rubella immunization is the protection of a future fetus against damage from intrauterine infection. Although rubella cases are reported routinely on college campuses, most colleges make no effort at controlling these outbreaks or instituting immunization requirements. The ACIP strongly urges educational institutions to require proof of immunity to rubella for registration or employment.