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 pilot study of the contribution of empathy to burnout in Salvation Army Officers

Although empathy has been found to distinguish effective counsellors from less effective counsellors, human services professionals who continually experience negative emotional reactions to the feelings that clients express in counselling may be at risk of developing burnout. This study examined the hypothesis that emotional empathy rather than cognitive empathy is associated with burnout. The sample of human services professionals consisted of 71 Salvation Army Officers. Multiple regression was used to investigate whether the dimensions of empathy could predict three aspects of burnout: personal accomplishment, emotional exhaustion and depersonalization. The first regression analysis indicated that personal distress and empathic concern were significant predictor of personal accomplishment. The second analysis indicated that personal distress was a significant predictor of emotional exhaustion. The third indicated that empathic concern was a significant predictor of depersonalization. Although these results support the hypothesis, personal distress was negatively associated with personal accomplishment, whereas empathic concern was positively associated with personal accomplishment. The small size of the sample may have influenced the reliability of the findings. A multidimensional approach to the role of empathy in counselling may help human services professionals to manage their emotional reactions when they engage in counselling with distressed clients.     

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.     

The Social Context of Police Lying

This is an analysis of the social context of normal police lies. We define lies as speech acts which the speaker knows are misleading or false, are intended to deceive, and where evidence to the contrary is known to the observer. Lies are relative to a moral context, and what an audience will accept. Lies include excuses, which deny full responsibility for an act, but acknowledge its immorality, and justifications, which accept responsibility but deny blame-worthiness. Police learn to lie and to carefully distinguish normal (or acceptable) lies from unacceptable lies, suggesting that lies are a part of a negotiated occupational order. We show how and why some types of lies are rewarded by police using ethnographic data from an 18 month field study of a large urban force. Lies can be of little issue, or become troublesome. We report and analyze two kinds of troublesome lies: case lies, recognized stories an officer utilizes in a courtroom or on paper to facilitate the conviction of a suspect, and cover stories, lies an officer tells in court, to supervisors, and on the job with the aim of providing a verbal shield or mitigation in the event of discipline. Both excuses and justifications are woven together in these vignettes. An example of a refusal to lie is used to illustrate some of the limits on lying as well organizational factors in lying. Some implications for official lying are also noted.     

A modified false discovery rate multiple-comparisons procedure for discrete data, applied to human immunodeficiency virus genetics

Summary.  To help to design vaccines for acquired immune deficiency syndrome that protect broadly against many genetic variants of the human immunodeficiency virus, the mutation rates at 118 positions in HIV amino-acid sequences of subtype C versus those of subtype B were compared. The false discovery rate (FDR) multiple-comparisons procedure can be used to determine statistical significance. When the test statistics have discrete distributions, the FDR procedure can be made more powerful by a simple modification. The paper develops a modified FDR procedure for discrete data and applies it to the human immunodeficiency virus data. The new procedure detects 15 positions with significantly different mutation rates compared with 11 that are detected by the original FDR method. Simulations delineate conditions under which the modified FDR procedure confers large gains in power over the original technique. In general FDR adjustment methods can be improved for discrete data by incorporating the modification proposed.