Minimum variance unbiased estimation based on bootstrap iterations

Practical computation of the minimum variance unbiased estimator (MVUE) is often a difficult, if not impossible, task, even though general theory assures its existence under regularity conditions. We propose a new approach based on iterative bootstrap bias correction of the maximum likelihood estimator to accurately approximate the MVUE. Viewing bootstrap iteration as a Markov process, we develop a computational algorithm for bias correction based on arbitrarily many bootstrap iterations. The algorithm, when applied parametrically to finite sample spaces, does not involve Monte Carlo simulation. For infinite sample spaces, a nonparametric version of the algorithm is combined with a preliminary round of Monte Carlo simulation to yield an approximate MVUE. Both algorithms are computationally more efficient and stable than conventional simulation-based bootstrap iterations. Examples are given of both finite and infinite sample spaces to illustrate the effectiveness of our new approach. Supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China (Project No. HKU 7026/97P).     

The collective/affective practice of cancer survivorship

Whether within an atmosphere of hope, or amidst relations of fear, the emotions of cancer are unavoidably collectively produced. Yet persistent individualistic paradigms continue to obscure how the emotions of cancer operate relationally – between bodies, subjects, discourses, and practices – and are intertwined with circulating beliefs, cultural desires, and various forms of normativity. Drawing on interviews with 80 people living with cancer in Australia, this paper illustrates why recognition of the collective enterprise of survivorship – and the collective production of emotion, more generally – is important in light of persistent, culturally dominant conceptions of the individual patient as the primary ‘afflicted’, ‘feeling’, and ‘treated’ subject. Building on previous work on affective relations and moral framings, we posit that the collective affects of survivorship inflect what people living with cancer can, and should, feel. We highlight how such things as hope, resignation, optimism, and dread are ‘products’ of the collective affects of cancer, with implications for how survivorship is lived, felt, and done.     

Reanalysis of Dose-Response Data from the Iraqi Methylmercury Poisoning Episode

Applying a hockey stick parametric dose-response model to data on late or retarded development in Iraqi children exposed in utero to methylmercury, with mercury (Hg) exposure characterized by the peak Hg concentration in mothers'hair during pregnancy, Cox et al. calculated the "best statistical estimate" of the threshold for health effects as 10 ppm Hg in hair with a 95% range of uncertainty of between 0 and 13.6 ppm.⁽¹⁾A new application of the hockey stick model to the Iraqi data shows, however, that the statistical upper limit of the threshold based on the hockey stick model could be as high as 255 ppm. Furthermore, the maximum likelihood estimate of the threshold using a different parametric model is virtually zero. These and other analyses demonstrate that threshold estimates based on parametric models exhibit high statistical variability and model dependency, and are highly sensitive to the precise definition of an abnormal response. Consequently, they are not a reliable basis for setting a reference dose (RfD) for methylmercury. Benchmark analyses and statistical analyses useful for deriving NOAELs are also presented. We believe these latter analyses—particularly the benchmark analyses—generally form a sounder basis for determining RfDs than the type of hockey stick analysis presented by Cox et al. However, the acute nature of the exposures, as well as other limitations in the Iraqi data suggest that other data may be more appropriate for determining acceptable human exposures to methylmercury.     

National consistency and provincial diversity in delivery of long-term care in Canada

The aim of this article is to demonstrate the diversity in delivery of long-term care at the provincial level, within a national legislative framework that provides universal health insurance and public administration. Not all provinces have legislated provision of long-term care, but mandates for provincial long-term care programs typically address the needs of those with chronic health needs and maintain them in the community for as long as possible. Eligibility is based on common criteria of residency, health need, facility, assessment, and consent. The three common components of the service delivery system are institutional care, community-based services, and home-based services; the kinds of services within each component and the mix among them vary from province to province. There are also five common features in provincial service delivery systems: single point of entry, assessment, client classification, case management, and single administration. Throughout the article, examples from different provinces show the varying ways in which these aspects of service delivery have been addressed, and recent innovations have furthered this diversity. A detailed account of quality management systems also shows that while all provinces have adopted a common set of principles, they use a range of methods to pursue quality of care and to promote good practice.     

Correlation Between Carcinogenic Potency of Chemicals in Animals and Humans

Twenty-three chemicals were selected for comparison of the carcinogenic potencies estimated from epidemiological data to those estimated from animal carcinogenesis bioassays. The chemicals were all those for which reasonably strong evidence of carcinogenicity could be found in humans or animals and for which suitable data could be obtained for quantifying carcinogenic potencies in both humans and animals. Many alternative methods of analyzing the bioassay data were investigated. Almost all of the methods yielded potency estimates that were highly correlated with potencies estimated from epidemiological data; correlations were highly statistically significant (p less than 0.001), with the corresponding correlation coefficients ranging as high as 0.9. These findings provide support for the general use of animal data to evaluate carcinogenic potential in humans and also for the use of animal data to quantify human risk.     

Understanding the needs of LGBTQ clients and their risk for commercial sexual exploitation: Training community mental health workers

Training on commercial sexual exploitation (CSE) and victimization of lesbian, gay, bisexual, transgender, and queer (LGBTQ) youths can increase awareness among professionals who provide services to this community. This study evaluated the effectiveness of a community-based training program geared toward mental health workers in a diverse metropolitan city. The training provided information about the continuum of sexuality and gender identity, sensitivity when working with LGBTQ clients, LGBTQ clients’ risks for CSE, and ways to improve service delivery to this population. Participants’ (N?=?64) knowledge level of these areas was examined prior to the training, immediately thereafter, and in a six-month follow-up. Participants showed an increase in knowledge from pretest to posttest. Follow-up testing on a limited sample revealed scores that were lower than posttest scores, but higher than pretest scores. Overall, through this community-based training, participants gained knowledge about the continuum of sexual and gender identity, appropriate service delivery when working with LGBTQ individuals, and the risk factors for CSE for LGBTQ youths. Participants also reported feeling satisfied with the training approach and format. Implications for future training to enhance mental health workers’ competence with LGBTQ victims of sexual exploitation are explored.     

Model-robust supersaturated and partially supersaturated designs

Supersaturated designs are an increasingly popular tool for screening factors in the presence of effect sparsity. The advantage of this class of designs over resolution III factorial designs or Plackett–Burman designs is that n, the number of runs, can be substantially smaller than the number of factors, m. A limitation associated with most supersaturated designs produced thus far is that the capability of these designs for estimating g active effects has not been discussed. In addition to exploring this capability, we develop a new class of model-robust supersaturated designs that, for a given n and m, maximizes the number g   of active effects that can be estimated simultaneously. The capabilities of model-robust supersaturated designs for model discrimination are assessed using a model-discrimination criterion, the subspace angle. Finally, we introduce the class of partially supersaturated designs, intended for use when we require a specific subset of _m1$m_1$ core factors to be estimable, and the sparsity of effects principle applies to the remaining (m-_m1$m-m_1$) factors.