Comparing Estimates of the Effects of Air Pollution on Human Mortality Obtained Using Different Regression Methodologies

Studies using regression techniques report their results using a variety of statistics. Evaluation of the consistency of findings, such as in a metaanalysis, requires calculating the statistical estimates of the effect reported in each study in a comparable manner. In this paper, we consider multiple linear regression, multiple Poisson regression, and logistic regression estimates. We present results that are needed to calculate, on a common basis, the slope of the regression function at a specified value, the elasticity function of the regression function at a specified value, the relative risk at a specified value, and the odds ratio at a specified value. We apply these results to studies of the association of daily mortality in an area to the daily air pollution level of ozone and PM₁₀. We calculate the estimated slope of the number of deaths per billion population associated with an increase of 1 ppb of ozone level in studies of daily mortality in three urban areas. These studies, in Los Angeles, New York, and St. Louis, produced very comparable results on a common basis, especially when compared to the coefficients as reported. We also calculated the estimated elasticity function of the daily mortality and daily PM₁₀ level for eight areas and found that the elasticities varied within a factor of roughly two, much less than the variability in the coefficients as reported.     

Individual vs. household determinants of the demand for medical care: A study of rural families

This article investigates, from a household perspective, the demand for medical care. Earlier (economic) studies have typically focused on individual utilization patterns; however, the data set employed here allows for an investigation of the role of other family members on individual demand. The theoretical results suggest that the labor force status (via the wage rate) of one family member may, in addition to influencing that person's rate of medical care use, effect the utilization of other household members. Separate physician visit demand equations are estimated for husbands, wives, and the household unit. The empirical results indicate that the wife's (full) cost of receiving medical care is a significant determinant of utilization by both the husband and other family members. Overall, the findings suggest that demand studies should take the presence of other household members and family structure into consideration when analyzing the determinants of individual medical care utilization.This study was supported in part by grant no. 1R03 HSO 2417-01 from the National Center for Health Services Research, HHS.Laurence Miners received his Ph.D. in economics from the University of North Carolina at Chapel Hill. He is currently an Associate Professor at Fairfield University and his research interests are focused mainly in the areas of health and labor economics. Correspondence concerning this article should be addressed to Laurence Miners, Department of Economics, Fairfield University, Fairfield, CT 06430.     

Nonparametric estimation of the limiting availability

The point availability of a repairable system is the probability that the system is operating at a specified time. As time increases, the point availability converges to a positive constant called the limiting availability. Baxter and Li (1994a) developed a technique for constructing nonparametric confidence intervals for the point availability. However, nonparametric estimators of the limiting availability have not previously been studied in the literature. In this paper, we consider two separate cases: (1) the data are complete and (2) the data are subject to right censorship. For each case, a nonparametric confidence interval for the limiting availability is derived. Applications and simulation studies are presented.deceased after the paper was accepted     

How Does Public Management Affect Government Performance? Findings from International Research

Despite the growing importance of public management reform aroundthe world, relatively little scholarship evaluates the contributionsof public management to government performance, that is, tothe character and consequences of service provision by publicagencies. One study (Hill and Lynn 2005) evaluated over eighthundred American empirical studies that address issues of publicmanagement effectiveness in a wide variety of fields, subfields,and disciplines. In this article we employ the analytic frameworkof Hill and Lynn—a polycentric "logic of governance"—toevaluate 193 research articles published in English that usenon-American, or what we will term international, empiricalevidence. Our evaluation reveals more similarities in Americanand non-American public management research, and in the determinantsof government performance, than one might expect, given thedistinctiveness of the American politico-administrative system.These similarities may be deceptive, however. Internationalinvestigators exhibit somewhat different modeling strategies,tending, for example, to favor more linear managerialist hypotheses—changesin structure lead to changes outcomes, for example—thanAmerican research, which is more concerned with intragovernmentalcomplexities. The fact that the use of a polycentric logic ofgovernance revealed highly suggestive similarities and differencesin the determinants of performance in public organizations suggeststhe potential value of this kind of analytic strategy in bothsingle investigations and in meta-analyses of public managementreform.     

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.     

Returning to YTS: the long-term impact of youth training scheme participation

ABSTRACT

Shortly after leaving Leicester for Scotland Andy Furlong began to wrestle with the complexities of school to work transitions as captured by the 1986 sweep of the British Cohort Study (BCS). His analysis was published as Schooling for Jobs. Although a relatively short text, this book was vitally important as it documented in detail, for the first time, the changes to career preparations of British secondary school children at the mid-point of a decade where the impact of deindustrialising processes, coupled with the neo-liberal policies of the political right, had ravaged the UK economy and decimated the youth labour market. The mid 1980s were a turning point that marked a shift to ‘individuals’ having responsibility for future career successes and the blaming of young people themselves for any perceived labour market failings. Central to this process was the Youth Training Scheme (YTS). Based on recent collaborations with Andy exploring YTS we have two main aims here. First, we revisit the BCS data to update the story and answer three interrelated questions: (i) what happened to the YTS participants from Furlong’s analysis?; (ii) what were the long-term career and life ‘impacts’ for those who participated in YTS during the 1980s?; and (iii) were these job substitution schemes or gateways to real and meaningful work? Second, we conclude by reflecting upon this aspect of Andy’s legacy and the shape of future research on youth training schemes.     

Transdiagnostic mechanisms involved in nonsuicidal self-injury,risky drinking and disordered eating: Impulsivity,emotion regulation and alexithymia

Abstract

Objective: The aim of the present study was to explore common and differential relationships between nonsuicidal self-injury (NSSI), risky drinking, and disordered eating attitudes and impulsivity, emotion dysregulation, and alexithymia. Methods: We investigated these associations in a sample of 951 college students (79.4% female, Mage = 21.86?years) by means of self-report questionnaires assessing the constructs of interest. Results: Overall, 28% of the students reported a history of NSSI, one third engaged in risky drinking, and less than 5% reported disordered eating symptoms. Negative urgency and difficulties in emotion regulation were both related to each of the three behaviors and can be considered as common transdiagnostic mechanisms. Conclusions: We discuss the implications of transdiagnostic mechanisms involved in these three dysregulated behaviors with respect to their assessment and treatment in college counseling settings.