Which Wald statistic? Choosing a parameterization of the Wald statistic to maximize power in k-sample generalized estimating equations

The Wald statistic is known to vary under reparameterization. This raises the question: which parameterization should be chosen, in order to optimize power of the Wald statistic? We specifically consider k-sample tests of generalized linear models (GLMs) and generalized estimating equations (GEEs) in which the alternative hypothesis contains only two parameters. An example is presented in which such an alternative hypothesis is of interest. Amongst a general class of parameterizations, we find the parameterization that maximizes power via analysis of the non-centrality parameter, and show how the effect on power of reparameterization depends on sampling design and the differences in variance across samples. There is no single parameterization with optimal power across all alternatives. The Wald statistic commonly used under the canonical parameterization is optimal in some instances but it performs very poorly in others. We demonstrate results by example and by simulation, and describe their implications for likelihood ratio statistics and score statistics. We conclude that due to poor power properties, the routine use of score statistics and Wald statistics under the canonical parameterization for GEEs is a questionable practice.     

Bootstrap Estimation of Benchmark Doses and Confidence Limits with Clustered Quantal Data

The benchmark dose (BMD) is an exposure level that would induce a small risk increase (BMR level) above the background. The BMD approach to deriving a reference dose for risk assessment of noncancer effects is advantageous in that the estimate of BMD is not restricted to experimental doses and utilizes most available dose-response information. To quantify statistical uncertainty of a BMD estimate, we often calculate and report its lower confidence limit (i.e., BMDL), and may even consider it as a more conservative alternative to BMD itself. Computation of BMDL may involve normal confidence limits to BMD in conjunction with the delta method. Therefore, factors, such as small sample size and nonlinearity in model parameters, can affect the performance of the delta method BMDL, and alternative methods are useful. In this article, we propose a bootstrap method to estimate BMDL utilizing a scheme that consists of a resampling of residuals after model fitting and a one-step formula for parameter estimation. We illustrate the method with clustered binary data from developmental toxicity experiments. Our analysis shows that with moderately elevated dose-response data, the distribution of BMD estimator tends to be left-skewed and bootstrap BMDL s are smaller than the delta method BMDL s on average, hence quantifying risk more conservatively. Statistically, the bootstrap BMDL quantifies the uncertainty of the true BMD more honestly than the delta method BMDL as its coverage probability is closer to the nominal level than that of delta method BMDL. We find that BMD and BMDL estimates are generally insensitive to model choices provided that the models fit the data comparably well near the region of BMD. Our analysis also suggests that, in the presence of a significant and moderately strong dose-response relationship, the developmental toxicity experiments under the standard protocol support dose-response assessment at 5% BMR for BMD and 95% confidence level for BMDL.     

Adult Drug Treatment Courts: A Review

Drug treatment courts (DTCs), an alternative to traditional criminal courts, provide an innovative way to legally process some drug offenders. The origin and recent growth of the drug court system in the USA can be explained as an unintended consequence of a failing 'war on drugs'. In this article, we discuss the spread of adult DTCs throughout the USA, the main components of drug courts, controversies surrounding DTCs, and some criticisms of drug courts. We summarize the recent evaluations of adult DTCs, and highlight various DTC factors that have been found to reduce individual drug use and criminal activity. We also offer suggestions for future research on DTCs and conclude with policy recommendations.     

Glass ceilings or sticky floors? A model of high-income law graduates

Minorities and females are underrepresented in the top-income quintile of law school graduates. Employing a binary logistic regression model, I examine whether this is due to a“glass ceiling” (an invisible barrier erected by third parties) or a“sticky floor” (self-imposed limitations regarding employment). My major finding is that being female, a minority, or disabled did not significantly reduce one's probability of making the top-income quintile once hours of work, experience, and other factors are taken into account. My findings directly contradict the large body of glass-ceiling literature and support the sticky-floor model. I thank the Law School Admission Council for funding this research. Helpful comments and suggestions were received from Robert Nelson of Northwestern University and the American Bar Foundation, Steven Conroy of the University of West Florida, and R. Kim Craft and Douglas Bonzo of Southern Utah University. The views expressed here are solely those of the author and do not necessarily reflect those of the institutions or persons listed above.     

Joint tests of non-nested models and general error specifications

This paper is concerned with joint tests of non-nested models and simultaneous departures from homoskedasticity, serial independence and normality of the disturbance terms. Locally equivalent alternative models are used to construct joint tests since they provide a convenient way to incorporate more than one type of departure from the classical conditions. The joint tests represent a simple asymptotic solution to the “pre-testing” problem in the context of non-nested linear regression models. Our simulation results indicate that the proposed tests have good finite sample properties.     

The risky business of insurance pricing

The factors influencing insurance pricing decisions are assessed using the ISO product liability ratemaking files for 1980–1984. The mean loss level has a strong positive effect on manual rates and premium rates/exposure. Evidence on a variety of ambiguity measures is more mixed. As a broad generalization, risk ambiguity lowers manual rates, which may reflect exclusion of large loss outliers as being unrepresentative. Risk ambiguity tends to have a positive effect on actual pricing decisions for particular policies, especially bodily injury lines and the interactive risk-ambiguity model.     

Construction and selection of quick switching double-sampling system: sample size tightening

A new sampling inspection system involving normal and tightened plans is presented. Performance measures are developed. The average sample number of the newly developed system is compared with those of existing plans. Procedures are indicated an tables are constructed for designing the system indexed by various combinations of parameters.