Closed Sequential and Multistage Inference on Binary Responses With or Without Replacement

Logistic regression is used by practitioners and researchers in many fields, but is undoubtedly used most frequently in medical and biostatistical applications. Maximum likelihood is generally the estimation method of choice, but we show that maximum likelihood can produce very poor results under certain conditions. Specifically, the poor performance of maximum likelihood in the case of rare events is known and we review research on this topic. We primarily examine the performance of maximum likelihood in the presence of near separation, which has apparently not been studied. Exact logistic regression is the logical alternative to maximum likelihood. We offer a comparison of the two methods of estimation.     

Free riders and the redistributive effects of international commodity agreements: The Case of Coffeee

Most studies on the redistributive effects of international commodity agreements neglect the existence of free riders. This article shows, however, that incentives for a free rider behavior may exist under various systems of commodity control. The International Coffee Agreement includes an export quota scheme that is faced with free riders on the import side. The factors that determine the impacts of such a scheme on prices, trade, earnings, and expenditures on the world market and on welfare of importing nonmember countries are elaborated theoretically. An econometric model of the world coffee market is then used to measure the effects of coffee export quotas on different variables of the world market. By use of estimated national import demand functions for coffee, the national welfare gains of importing nonmember countries due to the quota policy of the International Coffee Agreement are also computed.     

Wife or frau,women do worse: A comparison of men and women in the United States and Germany after marital dissolution

Longitudinal data from the Panel Study of Income Dynamics and the German Socio-Economic Panel show that in the Federal Republic of Germany, women experience even sharper drops in economic status immediately after a marital split than in the United States, while German and American men fare about the same. German social policy does little to reduce the disparities.     

Effort-reward imbalance,overcommitment and sleep in a working population

The relationship between workplace characteristics and nocturnal sleep in a working population was investigated. Data from 709 employees (mean age=39 years; 87% men) from two German companies were analysed at the entry of the longitudinal cohort study (overall accrual 73%). We investigated the association between the effort-reward imbalance model at work (Siegrist, ) and self-reported sleep quality and sleep disturbances, as assessed by the Jenkins Sleep Quality Index. Effort and overcommitment were found to be higher, and reward was lower in participants with lower (N=328) vs. higher sleep quality (N=381), as well as in participants with (N=217) vs. without (N=492) disturbed sleep (all ps<.001). In regression analyses, lower sleep quality (R ²=.33) and sleep disturbances (R ² _Nagelkerke=.33) were predicted by older age, female gender (only significant for sleep disturbances), shift-work, lower physical and mental health functioning, and higher overcommitment. Individuals were 1.7 times more likely to report disturbed sleep per standard deviation increase in overcommitment. Gender-stratified analyses revealed that higher overcommitment was associated with unfavourable sleep in men, while in women poor sleep was related to lower reward. The findings suggest that overcommitment at work interferes with restful sleep in men, while in women disturbed sleep may be associated with the amount of overcommitment and perceived job reward and sleep quality associated with the perceived reward.     

Reclaiming Life: Six Consumers of Mental Health Services Talk About What Helped and What Did Not Help Them Get Their Lives Back

This article summarizes a roundtable discussion held at Thresholds in Chicago, Illinois in September 2012, where six people diagnosed with serious mental illness talked about what helped and did not help them recover and successfully reclaim their lives. Their comments, taken as part of their personal narratives, can help enhance understanding of the recovery process. The discussion is organized by the themes that emerged: considering life as distinct from diagnosis, meeting basic needs, empowerment, education, community, faith and hope, healthy thinking, peers, and focus on wellness. Panel members also offer advice for mental health service providers.     

Can I Speak and Do You Hear Me? Quest(ion)s for R/Evolution

Young people have been and will always be the vanguards and visionaries of civil rights movements and liberation-oriented communities. Young queers, however, are still struggling to be heard, even within gay, lesbian, bisexual, and transgender communities. The author offers the Encounter-Reaction Model as an analytical framework to explore the dynamics of power and oppression from the top-down perspective. He also raises probing questions to those in authority on their knowledge of disenfranchised communities' identities and realities, their strategies for leadership development, inclusion and accountability, and their motivations in regard to working and structuring their relationships with those at the margins. Finally, he unpacks the roots and manifestations of being silenced.     

Effective strategies in emerging industries

This paper presents the methodology and the results of an extensive field study achieved in 1982–1983, focusing on industrial firms' strategies in two emerging industries. Fiftynine firms participated in this work. Four generic strategies consistent with survival were identified, one of them being the most effective for building market share. Complementary studies are needed to test the external validity of these results.