Exact Confidence Intervals for Proportions Estimated by Group Testing with Different Group Sizes

Group testing is the process of combining individual samples and testing them as a group for the presence of an attribute. The use of such testing to estimate proportions is an important statistical tool in many applications. When samples are collected and tested in groups of different size, complications arise in the construction of exact confidence intervals. In this case, the numbers of positive groups has a multivariate distribution, and the difficulty stems from a lack of a natural ordering of the sample points. Exact two‐sided intervals such as the equal‐tail method based on maximum likelihood estimation, and those based on joint probability or likelihood ratio statistics, have been previously considered. In this paper several new estimators are developed and assessed. We show that the combined tails (or Blaker) method based on a suitable ordering statistic, is the best choice in this setting. The methods are illustrated using a study involving the infection prevalence of Myxobolus cerebralis among free‐ranging fish.     

On the role of statistics in the palaeomagnetic proof of continental drift

Magnetized rocks provide a “tape recording” of the more recent history of the earth. It was this evidence that broke the opposition to continental drift. The nature of the data - samples of unit vectors in three dimensions - demanded new forms of statistical treatment. I hope that my personal account will enable the general statistician to see a rare example of statistics being developed to be a modest help in a major scientific revolution.     

Partially balanced incomplete block designs with two associate classes

We provide constructions of cyclic 2-class PBIBD's using cyclotomy in finite fields. Our results give theoretical explanations of the two sporadic examples given by Agrawal (1987).     

Is automatic enrollment consistent with a life cycle model?

We examine retirement saving for young adults in a life cycle model. We find that optimal retirement saving is zero for liquidity-constrained young adults who anticipate significant earnings growth. With a plausible age-earnings profile for college-educated workers, retirement saving does not begin until the late 30s or early 40s. Workers facing a flat earnings profile begin saving much sooner. Participating may be optimal for younger workers facing steep earnings profiles if they anticipate switching jobs and cashing out after 1–2 years. Our results suggest that automatically enrolling workers, regardless of age, is not consistent with a life cycle model.     

Binge Drinking During the First Semester of College: Continuation and Desistance From High School Patterns

Abstract

Students' first semester on campus may set the stage for their alcohol use/misuse throughout college. The authors surveyed 274 randomly sampled first-semester freshmen at a large southwestern university on their past 2 weeks' binge drinking, their high school binge drinking, and psychosocial factors possibly associated with drinking. They conducted separate analyses among high school nonbinge drinkers (testing for predictors of college binge onset vs continued nonbinge drinking) and high school binge drinkers (testing for predictors of continued binge drinking in college vs desistance from drinking). In both analyses, the variables that predicted college binge drinking largely revolved around gregarious socializing (eg, partying, having a social network of individuals who drank relatively heavily). Gender was predictive only among high school nonbinge drinkers; women had a higher probability than did men of adopting binge drinking in college.     

Impugning the Humanitarian Defence

This article examines the claim that democratic states are justified in restricting access to asylum seekers on the grounds that failing to do so reduces public support for humanitarian refugee policies – referred to here as the humanitarian defence. Drawing on detailed historical, comparative and interpretive analysis of migration policy in Canada and Australia, the author builds on Matthew Gibney’s development of practically guided normative theory to assess cases in which political elites may legitimately enact restrictive policies in response to strong public opposition. Challenging the normative basis of the humanitarian defence, the article engages in a detailed discourse analysis of asylum crises in Canada (1987, 1999) and Australia (1979, 2001). The findings suggest that political elites do not respond to an independently arrived at, and objectively established, public opinion as implied in the humanitarian defence. Rather, political elites play a crucial role in shaping the discourse on asylum seekers and consequently, influence the very “public opinion” to which they claim to be responding. The author concludes that political elites should attempt to foster an environment in which the public accepts international obligations to refugees but accepts that in some cases political elites may be justified in implementing restrictive measures.     

Comparisons in Gender Wage Differentials and Discrimination between Germany and the United Kingdom

Due to the lack of consistent data, direct and robust comparisons of cross‐country labour markets have been virtually impossible. This study uses a new panel data series that controls for inconsistencies, thus overcoming this problem. This study estimates gender wage differentials and gender discrimination in the German and UK labour markets. Panel estimates are used to identify general wage differences between the two countries, with cross‐sectional comparisons undertaken to identify changes that have occurred between 1991 and 1993, that are consistent with known labour market policies. It is found that gender wage differentials are greater in the UK than Germany with employer discrimination against females attributed with the majority of the difference in both countries.     

Just a paper exercise?

This paper will consider the impact and implications of changing the method of selection for social work students on one BA/Diploma in social work course for mature students with family commitments. The change was instituted following research which suggested that interviewers' preferences were a poor predictor of successful outcome of course completion for students, and further, that other predictors such as quality of written application material and student motivation were factors which had a strong correlation with successful outcome. Consequently, in 1999, selecting students by interview was replaced by paper selection. While it is the long-term aim of academic staff to evaluate the merits of paper selection in terms of students' outcomes, this initial paper considers the organisational and administrative implications of changing to paper selection and the students' and selectors' perceptions of paper selection. In particular, this paper will consider whether it is possible to be objective in selecting applicants, or whether subjectivity will always be part of the process. Finally, the article considers the relative cost of paper selection as opposed to interview. The findings of this study suggest that interviewing is twice as costly on academic and agency staff time - a factor which in the present financial climate has considerable implications for the future of interviewing on social work courses.     

Social Work Values in Human Services Administration: Implications for Social Work Education

The perceived wisdom in the social work education community, based on empirical research from the 1990s and the early part of this century, says that the master of social work (MSW) degree is not competitive with the master of business administration or the master of public administration to obtain top-level administration jobs in nonprofit agencies. This article reviews recent information on hiring preferences of board chairs that provides new hope that the MSW degree with a concentration in management or administration is perceived as a viable and useful degree for top-level positions in human services agencies. Thus, current board chairs are more inclined to value the MSW than administrators and academics from years past. The reason is that the values of social workers are seen as quite valuable in the current environment.     

“I Felt Like I Was Being Abused All Over Again”: How Survivors of Child Sexual Abuse Make Sense of the Perinatal Period Through Their Narratives

ABSTRACT

Sequelae following child sexual abuse pervade the lives of adult survivors, significantly impacting on pregnancy and childbirth. Symptoms of this distress are recognized, but meanings for women are less understood. This research aimed to examine the meaning for women themselves of the impact of child sexual abuse on experiences of pregnancy, childbirth, and the postnatal period. Taking a critical feminist perspective, three open-ended interviews with three survivors enabled women’s narratives of pregnancy and childbirth to be heard, explored the structure of these narratives, including how experiences were connected, and identified key themes and how selves and others were positioned. Women themselves contributed to the analysis of their own narratives. The different struggles of each woman occurred within three domains of experience: identity, embodiment, and parenting. They were underpinned by a fluctuation between empowerment and disempowerment. These findings, although based on detailed analysis of the experiences of only three women, dovetail with, integrate, and extend the existent literature, offering a framework for understanding the complexity of meaning making for women. Further research might develop this. The framework may facilitate clinicians’ understandings of what it is like for some women having children who have experienced child sexual abuse.