Robust estimation methods for exponential data: a monte-carlo comparison

We compare the performance of seven robust estimators for the parameter of an exponential distribution. These include the debiased median and two optimally-weighted one-sided trimmed means. We also introduce four new estimators: the Transform, Bayes, Scaled and Bicube estimators. We make the Monte Carlo comparisons for three sample sizes and six situations. We evaluate the comparisons in terms of a new performance measure, Mean Absolute Differential Error (MADE), and a premium/protection interpretation of MADE. We organize the comparisons to enhance statistical power by making maximal use of common random deviates. The Transform estimator provides the best performance as judged by MADE. The singly-trimmed mean and Transform method define the efficient frontier of premium/protection.     

‘A Blinding Lack of Progress’: Management Rhetoric and Affirmative Action

In this study we explore how versions of organizational reality and gender are constructed in management discourse and whether such patterns change over time. Specifically, we examine management explanations and accounts of the gendered nature of their organizations through their commentaries on their affirmative action programmes. In Australia private sector organizations with 100 or more employees are required to report to government on their affirmative action programmes for women. In these documents, management representatives outline objectives for the coming year and report on their progress in reducing employment‐related barriers for women. In doing so they account for the ‘problem’ of gender‐based discrimination that affirmative action is designed to address, justify their actions (or lack of action) and reproduce versions of gendered identity. Thus we use affirmative action reporting as cases of management rhetoric to explore how aspects of gender and organization are constructed, taken for granted, challenged or problematized. Comparing reports from the hospitality sector over a 14‐year period, we explore whether there is any evidence of discursive change in management accounts of the gendered nature of their organizations.     

The Limits of Self-Management: Community and Health Care System Barriers Among Latinos With Diabetes

Although numerous studies examine diabetes self-care, few regard ecological framework correlates such as community and institutional level factors as fundamental for understanding diabetes management for Latinos. This article addresses the dearth of research that exists regarding social contextual forces and diabetes management for Latinos. Given the scarcity of research on this topic, studies of non-Latino groups were reviewed to illustrate the importance of community and institutional influences on diabetes care. Consideration of fundamental correlates within the ecological framework may better discern the underlying rationale for inadequate diabetes self-management for individuals who live in impoverished communities.     

Computer integrated management—The next competitive breakthrough

This article addresses the key question of how organizational competitiveness can be achieved through leveraging the high impact potential of IT. Using the Wilmot 80/20 Rule of Management as his yardstick for measuring the performance of today's organizations, Dr Wilmot provides an insight into how the culture and decision making processes of the organization of 1992 will be transformed by the effective use of strategic, integrated information systems.     

The Utility of a Gender-Specific Definition of Binge Drinking on the AUDIT

Abstract

Objective: Although binge drinking is commonly defined as the consumption of at least 5 drinks in 1 sitting for men and 4 for women, the Alcohol Use Disorders Identification Test (AUDIT) defines binge drinking as the consumption of 6 or more drinks in 1 sitting for both men and women. This study examined the effect of using gender-specific binge drinking definitions on overall AUDIT scores. Participants: Participants were 331 college men and 1224 college women. Methods: Participants completed a self-report questionnaire, which included the AUDIT. Results: Findings showed that defining binge drinking as 4 or more drinks for women, rather than 6 or more, does impact their AUDIT scores and could affect the percentage of women classified as hazardous users. Among men, AUDIT scores were unaffected by the use of a gender-specific definition of binge drinking. Conclusions: Results suggest that the AUDIT might be underidentifying hazardous users among college women.