Conditional interval estimation of the mean following rejection of a two sided test

The effect of rejecting a two-sided preliminary test of significance for the mean of a normal distribution upon subsequent interval estimation of the mean is examined. For the case where the variance is known, conditional confidence intervals may be shorter than unconditional intervals, in contrast to the one-sided preliminary test case examined by Meeks and D’Agostino (1983, The American Statistician, 7, 134-136) . For the case where the variance is unknown and must be estimated by the sample variance, it is shown that customary intervals do not offer uniformly greater or lesser coverage than the nominal level.     

AN EXPERIMENTAL STUDY OF ALTERNATIVE CAMPAIGN FINANCE SYSTEMS: TRANSPARENCY,DONATIONS, AND POLICY CHOICES

We experimentally study the transparency effect of alternative campaign finance systems on donations, election outcomes, policy choices, and welfare. Three alternatives are considered: one where donors' preferences and donations are unobserved by the candidate and public; one where they are observed by the candidate but not the public; and one where they are observed by all. We label them full anonymity (FA), partial anonymity (PA), and no anonymity (NA), respectively. We find that in NA and PA candidates consistently respond to donations by choosing policies favoring the donors. FA, in contrast, is the most successful in limiting the influence of donations on policy choices. Donors benefit greatly from the possibility of donations whereas social welfare may be harmed in some treatments. To our knowledge, this article is the first to investigate the effect of different campaign finance systems distinguished by their transparency level. (JEL D72)     

“I Didn’t Feel Equipped”: Social Work Students’ Reflections on a Simulated Client “Coming Out”

Few studies have examined social work students’ reflections on and experiences working with lesbian, gay, bisexual, queer, and questioning persons and addressing the intersection of race/ethnicity and sexuality within practice. This study explored current master’s of social work student (n = 11) and recent graduate (n = 7) reflections on conducting an objective structured clinical practice interaction with an African Canadian youth coming out as a lesbian. Narrative thematic analyses of reflective dialogues highlighted a variation of competence in gay affirmative practice across attitudes (managing personal reactions), knowledge (addressing diversity; terminology and information), and skills (readiness; challenging heterosexism). Curriculum development and agency-based training is recommended to address gaps in knowledge and competence regarding gay affirmative approaches.     

Studying Individual and Family Development: Linking Theory and Research

The predominant theoretical orientation of the majority of scientists studying human behavioral development and family functioning is derived from systems models. These theories are dynamic in their conceptualization and emphasize process and context. To a large extent, the analytic strategies we employ are not consistent with our theoretical assumptions. Analytic methods that focus on moderating and mediating processes rather than main effects, on within‐group variability and the sources of that variability, and on the identification of interrelated patterns of change in individuals, families, and environments are needed for our research results to mirror the complexity of our theories.     

How close is too close?: The negative relationship between knowledge of HIV transmission routes and social distancing tendencies

Data measuring respondents’ knowledge of HIV's transmission routes was obtained via a statewide RDD sample of 603 Nevadans to determine if disease knowledge influences respondent efforts to socially and physically distance themselves from a hypothetical HIV-positive person. Four separate dependent variables (scenarios) are created in which the geographic distance between the respondent and a hypothetical HIV-positive person decreases; while, at the same time, physical personal contact, or potential for contact, increases. Findings show 84.2% of the respondents had sufficient knowledge of HIV transmission routes, and the majority felt comfortable across all four social scenarios. However, multiple logistic regression analyses indicate that respondents with sufficient knowledge of how HIV is transmitted are significantly more comfortable with casual social interactions than those respondents with insufficient knowledge. The results from this study confirm the importance of HIV-knowledge as a tool to combat AIDS-related stigma.     

A scientist's viewpoint on promoting effective use of experimental design: Ten things a scientist wants to know about experimental design

This paper tackles the practical application of statistical tools. Chemical development is a rich area for collaboration between statisticians and chemists, but most statisticians encounter difficulties in promoting the tools to this client group. This paper, presented from a chemist's perspective, is intended to help bridge the gap between the two professions. The paper explores differences in uptake and attitudes towards adopting these techniques and suggests what has hindered or helped the process of effective application of experimental design. Copyright © 2003 John Wiley & Sons, Ltd.     

Tree-structured subgroup analysis for censored survival data: Validation of computationally inexpensive model selection criteria

The performance of computationally inexpensive model selection criteria in the context of tree-structured subgroup analysis is investigated. It is shown through simulation that no single model selection criterion exhibits a uniformly superior performance over a wide range of scenarios. Therefore, a two-stage approach for model selection is proposed and shown to perform satisfactorily. Applied example of subgroup analysis is presented. Problems associated with tree-structured subgroup analysis are discussed and practical solutions are suggested.     

Access to Information and Internal Structures of Partisan Groups: Some Notes on the Iron Law of Oligarchy*

Michel's notion of the inevitable and ironic transformation of groups with egalitarian intent into groups with oligarchical practices is examined through an analysis of thirty-four role playing partisan groups. Each group is a triad with an extended shared history or a history of equality that comes with friendship. Each group differentiated itself by selecting a representative to confront another student who played the role of a university dean. In nineteen of the groups the constituents obtained a news report of the outcome of those negotiations independent of their representative's report. In the other fifteen groups the constituents had to depend on their representative's report. In those groups that relied solely on their representative's report, oligarchical interrelations emerged. This contrasts with the news report groups who maintained egalitarian relationships while developing a political standpoint toward each other, the opposition and the future. We conclude that Michels' statement on organizational oligarchy is illuminated further by a consideration of an emergent monopoly of knowledge.     

Performance of standard imputation methods for missing quality of life data as covariate in survival analysis based on simulations from the International Breast Cancer Study Group Trials VI and VII*

Abstract

Imputation methods for missing data on a time-dependent variable within time-dependent Cox models are investigated in a simulation study. Quality of life (QoL) assessments were removed from the complete simulated datasets, which have a positive relationship between QoL and disease-free survival (DFS) and delayed chemotherapy and DFS, by missing at random and missing not at random (MNAR) mechanisms. Standard imputation methods were applied before analysis. Method performance was influenced by missing data mechanism, with one exception for simple imputation. The greatest bias occurred under MNAR and large effect sizes. It is important to carefully investigate the missing data mechanism.