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.     

Portmanteau test for conditional heteroscedasticity, using ranks of squared residuals

Squared residual autocorrelations have been found useful in detecting departures from linearity in time series models. This is especially the case with data exhibiting heterogeneity in variances. A rank test is proposed which is much more robust than its parametric counterpart.     

Effects of Category Order on Answers in Mail and Telephone Surveys1

Abstract Past research suggests that mail surveys encourage a primacy effect, which is a tendency to choose the first answers from a list, whereas telephone surveys encourage a recency effect, a tendency to choose the last answers from a list. This paper summarizes results from 82 new experiments conducted in 12 separate surveys in seven states. Only four of 33 mail survey comparisons exhibited significant primacy effects, while five of 26 experiments in telephone surveys exhibited recency effects. In addition, only three of 23 cross-method comparisons produced a significant primacy/recency effect in the expected manner. The conclusion is that the prevalence of primacy and recency effects has been over-estimated by past research and a new theoretical approach that takes into account multiple causation is needed for examining these effects.     

Beyond recruitment: Predictors of differential participation in a national antihunger organization

Surprisingly little research has sought to explain differential participation after recruitment into social movement organizations (SMOs). This study examines the influence of several sets of predictors on participation by members of a national organization in the antihunger movement. The findings highlight the importance of incentive, ideological, and microstructural factors for differential participation and suggest that favorable perceptions of SMOs also promote participation. Final remarks address the implications of the findings for the social movement and voluntary organization literatures.     

log-logistic survival estimation based on failure-censored data

Approximations of the Bayesian estimators of the survival function based on the censored data of the log-logistic distribution are obtained under squared-error and log-odds squared-error loss functions. A numerical example is presented. Through a Monte Carlo simulation study, the behavior of the approximations found by Tierney & Kadane and Lindley are compared with a method suggested by Weiss & Howlader.     

A Process for Incorporating Comparative Risk into Environmental Policymaking in Louisiana

The goal of Louisiana's 1990–1991 comparative risk project, also called the Louisiana Environmental Action Plan (LEAP), was to incorporate risk assessment into state environmental planning and policymaking. Scientists, government officials, and citizens were brought together to estimate the relative risk to human health, natural resources, and quality of life posed by 33 selected environmental issues. The issues were then ranked according to their relative estimated risks. It was hoped that this ranking of "comparative risks" would enable state policymakers to target the most important environmental problems and allocate scarce public resources more rationally and efficiently. As a result of the project, the governor issued an Executive Order forming a permanent Public Advisory Committee to continue this type of comparative risk assessment in Louisiana.     

Significance of the Dermal Route of Exposure to Risk Assessment

The skin is a route of exposure that needs to be considered when conducting a risk assessment. It is necessary to identify the potential for dermal penetration by a chemical as well as to determine the overall importance of the dermal route of exposure as compared with inhalation or oral routes of exposure. The physical state of the chemical, vapor or liquid, the concentration, neat or dilute, and the vehicle, lipid or aqueous, is also important. Dermal risk is related to the product of the amounts of penetration and toxicity. Toxicity involves local effects on the skin itself and the potential for systemic effects. Dermal penetration is described in large part by the permeability constant. When permeability constants are not known, partition coefficients can be used to estimate a chemical's potential to permeate the skin. With these concepts in mind, a tiered approach is proposed for dermal risk assessment. A key first step is the determination of a skin-to-air or skin-to-medium partition coefficient to estimate a potential for dermal absorption. Building a physiologically-based pharmacokinetic (PBPK) model is another step in the tiered approach and is useful prior to classical in vivo toxicity tests. A PBPK model can be used to determine a permeability constant for a chemical as well as to show the distribution of the chemical systemically. A detailed understanding of species differences in the structure and function of the skin and how they relate to differences in penetration rates is necessary in order to extrapolate animal data from PBPK models to the human. A study is in progress to examine anatomical differences for four species.     

A measure of slope-rotatability for second order response surface experimental designs

In the design of experiments for estimating the slope of a response surface, slope-rotatability is a desirable property. In this paper, a measure is introduced that enables us to assess the degree of slope-rotatability for a given response surface design. The measure takes the value zero if and only if the design is slope-rotatable, and becomes larger as the design deviates from a slope-rotatable design. Examples of applying this measure to some response surface designs are also given.     

Pseudo–Modelling of Outliers for Estimation of Regression And Time Series Models

This paper documents situations where the variance inflation model for outliers has undesirable properties. The model is commonly used to accommodate outliers in a Bayesian analysis of regression and time series models. The alternative approach provided here does not suffer from these undesirable properties but gives inferences similar to those of the variance inflation model when this is appropriate. It can be used with regression, time series, and regression with correlated errors in a unified way, and adheres to the scientific principle that inference should be based on the data after obvious outliers have been discarded. Only one parameter is required for outliers; it is interpretable as the a priori willingness to remove observations from the analysis.