Approximate variance formulas and asymptotic joint sampling distributions of standardized risk ratios in the presence of competing risks in cohort studies

The present paper is concerned with some results in cohort studies, in which the individuals in two study population are exposed simultaneously to several risks of death, which compete for their lives.

The morality experience of individuals in the two study populations is compared with respect to the morality experience of individuals in a well-defined and fixed population called the standard population.

Under some reasonable assumptions, not only simple variance formulas are-developed for the standardized risk ratio statistics (S[Rcirc]R_i) but also their joint asymptotic sampling distribution. It is demonstrated that these SRcirc;R_i's have asymptotically a multivariate normal distribtion corresponding to any given number of competing risks of death, These results are utilized to construct Scheffé-type and Sidak-type simultaneous confidence intervals for the SRR_i parameters which hold regardless of any covariance structure among the competing risks of death. The corresponding results for the cause-specific SMR and the externally standardized risk ratio parameters follow as special cases.

The present paper generalizes the available results in the literature in two directions, namely, to obtain simple variance formulas for the S[Rcirc]R_i, statistics and to treat the situation in the presence of competing risks to which individuals in a study are simultaneously exposed.

An empirical evaluation of these results is discussed in the last section utilizing some real cohort data from two recent occupational epidemiologic cohort studies.     

Factors affecting the organizational responses of employers to workers with injuries

The organizational responses of employers to work-related injuries is one of several significant influences on return-to-work outcomes. Thus, understanding the factors that lead to better or worse organizational responses to work injuries may ultimately help to improve success in this area. The purpose of this study was to systematically explore factors that might influence the organizational responses of employers to injured workers, based on employee perceptions. Cross-sectional survey data were collected from 2,943 subjects with work-related injuries which had occurred less than eight weeks prior to survey completion. Measured variables included pre-injury demographic and job factors, injury circumstances, and a measure of post-injury events that comprised the organizational response. Multivariate linear regression results show that age, gender, job dissatisfaction before injury, prior difficulty performing job tasks, injury severity, back injury and lost time were all associated with negative organizational responses, suggesting potential opportunities for intervention.     

Undermining incentives: CEO reactions to compensation rebalancing

Directors commonly “punish” CEOs for overly risky behavior by rebalancing their compensation to include more restricted stock and fewer stock options. This paper extends the behavioral-agency model to describe how CEOs will manage their holdings of stock and stock options in response to this form of compensation rebalancing. In doing so, it finds that CEOs respond by selling existing stock holdings and accumulating option holdings. This behavior achieves the opposite incentive structure that such rebalancing intends to create, raising questions about the effectiveness of compensation rebalancing in reducing risky decision making.     

“We have a lot of goodwill, but we still need to eat…”: Valuing Women’s Long Term Voluntarism in Community Development in Lima

This paper focuses on recognizing the contribution made to development by grassroots women working on a voluntary basis in long term development projects. Using the example of healthcare, the paper problematizes the widespread move towards an increased reliance on voluntary and third sector provision. Drawing on literature around women’s community activism, the research considers the extent to which women carrying out health promotion work in Peru have taken on this role as more than “just voluntary work,” highlighting their long term commitment during more than a decade of health promotion activities. The paper develops debates around the professionalization of voluntary work, particularly considering the issue of economic remuneration for health promoters, and emphasizing the gendered nature of their voluntarism; concluding by questioning the sustainability of poor women’s long term, and largely unpaid, involvement as the linchpins of community development projects.

The Strengthening Families Programme (SFP) 10‐14 and substance misuse in Barnsley: the perspectives of facilitators and families

The aim of this study was to evaluate the Strengthening Families Programme for young people aged ten to 14 and their parents (SFP 10‐14) in Barnsley, a northern English city, based on the experience of facilitators and families who had participated in the programme. A mixed methods design blending both quantitative and qualitative data was used in the study carried out in two phases over a nine‐month period in 2005. Quantitative data were collected through: the SFP 10‐14 Parent/Caregiver Survey Questionnaire, the SFP 10‐14 Young Persons' Survey Questionnaire and the Strengths and Difficulties Questionnaire. Questionnaire data were compared at the beginning of the SFP 10‐14 programmes (weeks 1–2) and at the end of the programmes (week 7). In addition, two focus group meetings were held with families who had undertaken the SFP 10‐14 programme; and three focus group meetings were conducted with facilitators of SFP 10‐14 programmes. Once quantitative and qualitative data had been analysed separately, a synthesis of the main findings from both approaches was then completed. Following the programmes, parents reported significant changes in communication limit setting, emotional management, prosocial behaviour and drugs/alcohol use. Total difficulties scores were also significantly different pre‐ and post SFP 10‐14 programmes. For the young people, communication, and emotional management were improved and their drugs/alcohol use was less. Their total difficulties scores were also significantly different. Qualitative evidence indicated that families who participated in the study found the SFP 10‐14 useful in preventing young people's alcohol and drug use in terms of: learning more about alcohol and drugs, using knowledge and skills to reduce behaviours that might lead to alcohol and drug use and, for young people, dealing with peer pressure that might lead to drug and alcohol use. Parents/caregivers and young people reported that the SFP 10‐14 had played a part in improving family functioning through strengthening the family unit. The findings from this exploratory study suggest that the SFP 10‐14 may be a useful primary prevention intervention in helping to prevent drug and alcohol misuse in young people. Copyright © 2009 John Wiley & Sons, Ltd.     

The role of information in nonstationary regression

The role of standard likelihood-based measures of information and efficiency is unclear when regressions involve nonstationary data. Typically the standardized score is not asymptotically Gaussian and the standardized Hessian has a stochastic, rather than deterministic limit. Here we consider a time series regression involving a deterministic covariate which can be evaporating, slowly evolving or nonstationary. It is shown that conditional information, or equivalently, profile Kullback–Leibler and Fisher information remain informative about both the accuracy, i.e. asymptotic variance, of profile maximum likelihood estimators, and the power of point optimal invariant tests for a unit root. Specifically, these information measures indicate fractional, rather than linear trends that may minimize inferential accuracy. Such is confirmed in a numerical experiment.