The truncation-by-death problem: what to do in an experimental evaluation when the outcome is not always defined

Although experiments are viewed as the gold standard for evaluation, some of their benefits may be lost when, as is common, outcomes are not defined for some sample members. In evaluations of marriage interventions, for example, a key outcome--relationship quality--is undefined when a couple splits up. This article shows how treatment-control differences in mean outcomes can be misleading when outcomes are not defined for everyone and discusses ways to identify the seriousness of the problem. Potential solutions to the problem are described, including approaches that rely on simple treatment-control differences-in-means as well as more complex modeling approaches.     

Alcohol education provided to opioid treatment program patients: results of a nationwide survey

Alcohol-related problems are especially common among opioid treatment program (OTP) patients, suggesting that educating OTP patients about alcohol and its harmful effects needs to be a priority in OTPs. Using data collected in interviews with a nationwide U.S. sample of OTP directors (N = 200) in 25 states, we identified factors that differentiate OTPs that provided this education to all OTP patients from those that did not. Findings indicate that these factors include (1) providing this education in a greater variety of ways, (2) having a larger percent of staff knowledgeable about alcohol-related issues, (3) having a director who views alcohol issues as a high priority, and (4) having a written OTP policy.     

A meta-ethnographic study of health care staff perceptions of the WHO/UNICEF Baby Friendly Health Initiative

BackgroundImplementation of the Baby Friendly Health Initiative (BFHI) is associated with increases in breastfeeding initiation and duration of exclusive breastfeeding and ‘any’ breastfeeding. However, implementation of the BFHI is challenging.AimTo identify and synthesise health care staff perceptions of the WHO/UNICEF BFHI and identify facilitators and barriers for implementation.MethodSeven qualitative studies, published between 2003 and 2013 were analysed using meta-ethnographic synthesis.FindingsThree overarching themes were identified. First the BFHI was viewed variously as a ‘desirable innovation or an unfriendly imposition’. Participants were passionate about supporting breastfeeding and improving consistency in the information provided. This view was juxtaposed against the belief that BFHI represents an imposition on women's choices, and is a costly exercise for little gain in breastfeeding rates. The second theme highlighted cultural and organisational constraints and obstacles to BFHI implementation including resource issues, entrenched staff practices and staff rationalisation of non-compliance. Theme three captured a level of optimism and enthusiasm amongst participants who could identify a dedicated and credible leader to lead the BFHI change process. Collaborative engagement with all key stakeholders was crucial.ConclusionsHealth care staff hold variant beliefs and attitudes towards BFHI, which can help or hinder the implementation process. The introduction of the BFHI at a local level requires detailed planning, extensive collaboration, and an enthusiastic and committed leader to drive the change process. This synthesis has highlighted the importance of thinking more creatively about the translation of this global policy into effective change at the local level.     

Estimation of a multivariate normal covariance matrix under a certain structure

We consider the estimation of Σ of the p-dimensional normal distribution N_p (0, Σ) when Σ?=?θ₀ I_p ?+?θ₁ aa′, where a is an unknown p-dimensional normalized vector and θ₀?>?0, θ₁?≥?0 are also unknown. First, we derive the restricted maximum likelihood (REML) estimator. Second, we propose a new estimator, which dominates the REML estimator with respect to Stein's loss function. Finally, we carry out Monte Carlo simulation to investigate the magnitude of the new estimator's superiority.     

An asymptotic expansion of Wishart distribution when the population eigenvalues are infinitely dispersed

Takemura and Sheena [A. Takemura, Y. Sheena, Distribution of eigenvalues and eigenvectors of Wishart matrix when the population eigenvalues are infinitely dispersed and its application to minimax estimation of covariance matrix, J. Multivariate Anal. 94 (2005) 271–299] derived the asymptotic joint distribution of the eigenvalues and the eigenvectors of a Wishart matrix when the population eigenvalues become infinitely dispersed. They also showed necessary conditions for an estimator of the population covariance matrix to be tail minimax for typical loss functions by calculating the asymptotic risk of the estimator. In this paper, we further examine those distributions and risks by means of an asymptotic expansion. We obtain the asymptotic expansion of the distribution function of relevant elements of the sample eigenvalues and eigenvectors. We also derive the asymptotic expansion of the risk function of a scale and orthogonally equivariant estimator with respect to Stein’s loss. As an application, we prove non-minimaxity of Stein’s and Haff’s estimators, which has been an open problem for a long time.     

Answering the Call: Virtual Migration in Indian Call Centres

This paper explores the daily, psychic journeys Indian call center agents undergo as they ‘virtually migrate’ between India and the US. A thin cable that runs half way around the globe bridges the ‘here’ and the ‘there’, connecting agents to faraway customers in real time. The new time-space relations generated by this virtual contact create conditions for these workers to undergo a global ‘migration’ from India and to America, even as their bodies remain bounded within the national homeland. To accommodate the US American workday, Indian agents often work the nightshift and sleep during the day, leaving them little time for family, friends, and cultural events. This temporal arrangement displaces them from the daily rhythms of Indian life, generating a sense of loss, longing, and nostalgia for ‘India’. Further, while agents experience a sense of distance from India, they also experience a movement toward ‘America’. Agents’ accounts suggest a feeling of living between worlds, yet their movement is decoupled from physical migration.     

The Relationship Between Social Support and Subjective Well-Being Across Age

The relationships among types of social support and different facets of subjective well-being (i.e., life satisfaction, positive affect, and negative affect) were examined in a sample of 1,111 individuals between the ages of 18 and 95. Using structural equation modeling we found that life satisfaction was predicted by enacted and perceived support, positive affect was predicted by family embeddedness and provided support, and negative affect was predicted by perceived support. When personality variables were included in a subsequent model, the influence of the social support variables were generally reduced. Invariance analyses conducted across age groups indicated that there were no substantial differences in predictors of the different types of subjective well-being across age.