Peakedness for weighted sums of symmetric random variables

In this paper, we provide sufficient conditions on weighted coefficients under which the peakedness comparison between weighted sums of independent random variables can be carried out. These results extend and enrich the existing peakedness results in the literature including those presented by Proschan (1965) and Ma (1998).     

Sexual offenders' perceptions of their early interpersonal relationships: An attachment perspective

The present study examined the perceptions of early interpersonal experiences of sexual offenders (child molesters and rapists) and two criminal comparison groups. A grounded theory approach was applied to a comprehensive list of responses provided by the participants to questions about their early interpersonal experiences. The raw data was collapsed into 14 basic categories by grouping together responses of similar meanings. The categories were responsiveness, consistency, acceptance, boundaries, emotional regulation, autonomy, self‐evaluation, developmental trauma sexual abuse and deviation, physical abuse, loss, conflict, safety, and positive mediating interactions. In the second part of the study, the four groups were compared using the categories and the differences noted. All four groups experienced significantly negative early interpersonal experiences.     

The SLA DBIO 100 Poll: 100 Journals Voted by SLA’s BioMedical and Life Sciences Division as the Most Influential over the Last 100 Years

An expert opinion poll of the members of the BioMedical and Life Sciences Division (DBIO) of the Special Libraries Association (SLA), conducted on the occasion of the SLA's Centennial (Washington, DC, June 14–17, 2009), identified 100 journals across three major categories (Clinical Medicine and Allied Health Sciences, Journals Primarily Reporting Molecular and Cellular Biology, and Journals of Natural History) as the most influential over the last 100 years. The Top Ten, containing winners from all three of these groups, were also named, as were a “Journal” and a “Publisher” of the Centennial.”     

Hilda Mary Woods MBE, DSc, LRAM, FSS (1892-1971): reflections on a Fellow of the Royal Statistical Society

We have previously described the content of a text by Woods and Russell, An Introduction to Medical Statistics, compared it with Principles of Medical Statistics by Hill and set both volumes against the background of vital statistics up until 1937. The two books mark a watershed in the history of medical statistics. Very little has been recorded about the life and career of the first author of the earlier textbook, who was a Fellow of the Royal Statistical Society for at least 25 years, an omission which we can now rectify with this paper. We describe her education, entry into medical statistics, relationship with Major Greenwood and her subsequent career and life in Ceylon, Kenya, Australia, England and South Africa.     

Preliminary Goodness-of-Fit Tests for Normality do not Validate the One-Sample Student t

One of the most basic topics in many introductory statistical methods texts is inference for a population mean, μ. The primary tool for confidence intervals and tests is the Student t sampling distribution. Although the derivation requires independent identically distributed normal random variables with constant variance, σ², most authors reassure the readers about some robustness to the normality and constant variance assumptions. Some point out that if one is concerned about assumptions, one may statistically test these prior to reliance on the Student t. Most software packages provide optional test results for both (a) the Gaussian assumption and (b) homogeneity of variance. Many textbooks advise only informal graphical assessments, such as certain scatterplots for independence, others for constant variance, and normal quantile–quantile plots for the adequacy of the Gaussian model. We concur with this recommendation. As convincing evidence against formal tests of (a), such as the Shapiro–Wilk, we offer a simulation study of the tails of the resulting conditional sampling distributions of the Studentized mean. We analyze the results of systematically screening all samples from normal, uniform, exponential, and Cauchy populations. This pretest does not correct the erroneous significance levels and makes matters worse for the exponential. In practice, we conclude that graphical diagnostics are better than a formal pretest. Furthermore, rank or permutation methods are recommended for exact validity in the symmetric case.     

Marginal Correlation in Longitudinal Binary Data Based on Generalized Linear Mixed Models

This work aims at investigating marginal correlation within and between longitudinal data sequences. Useful and intuitive approximate expressions are derived based on generalized linear mixed models. Data from four double-blind randomized clinical trials are used to estimate the intra-class coefficient of reliability for a binary response. Additionally, the correlation between such a binary response and a continuous response is derived to evaluate the criterion validity of the binary response variable and the established continuous response variable.     

How has public policy shaped defined-benefit pension coverage in Canada?

Unlike federal regulation in the United States, variation in provincial regulation across Canada provides a natural laboratory to examine the impact of public policy on pension coverage. Using data from a nationally representative sample of private sector workers in Canada in 1994, we find that higher marginal taxes, earlier vesting, and more permissive eligibility rules increase coverage, while a ban on mandatory retirement has a negative, but insignificant effect. Implications for differences in defined-benefit coverage between Canada and the United States, and pension theory, research, and practice are discussed.