Multiple imputation compared with restricted pseudo‐likelihood and generalized estimating equations for analysis of binary repeated measures in clinical studies

Non‐likelihood‐based methods for repeated measures analysis of binary data in clinical trials can result in biased estimates of treatment effects and associated standard errors when the dropout process is not completely at random. We tested the utility of a multiple imputation approach in reducing these biases. Simulations were used to compare performance of multiple imputation with generalized estimating equations and restricted pseudo‐likelihood in five representative clinical trial profiles for estimating (a) overall treatment effects and (b) treatment differences at the last scheduled visit. In clinical trials with moderate to high (40–60%) dropout rates with dropouts missing at random, multiple imputation led to less biased and more precise estimates of treatment differences for binary outcomes based on underlying continuous scores. Copyright © 2005 John Wiley & Sons, Ltd.     

People as partners: Facilitating people's participation in public–private partnerships for solid waste management

Cities in developing countries are facing a double dilemma. On one hand, the urban population is growing rapidly, causing a huge increase in demand for waste management services. On the other hand, the traditional public sector is failing to respond to the increased demand for service. The public sector is constrained by resource and institutional limitations. It is often proposed that the solution lies in private sector participation. It is expected that the private sector, with its dynamism and flexibility, may fill in the service delivery gaps by forming partnership with the public sector. However, a third tier—the people—is often overlooked in the service delivery framework. Citizens can contribute significantly to service delivery. They can support the private sector with payment of service charges. But more importantly, they can play an active role in improving accountability and service quality of both public and private sector. This radical shift in people's role, from passive service receivers to active service partners, however, may not occur endogenously. External help from facilitating agencies may enable the public and private sector to form partnership with people for better service delivery. This article examines the role of facilitating agencies in developing tripartite partnership for solid waste management service in Bangladesh. The key lessons learned are: a number of obstacles prevented spontaneous partnership among the public sector, private sector and people; facilitating agencies were able to overcome the obstacles to form partnership of the three; and, the tripartite arrangement resulted in higher accountability and better service delivery.     

How Australian Female Muslim Students Interpret Challenges in High School Sports

Abstract

The present study focuses on the experiences of female Muslim students in school sporting activities in Australian public high schools. Specifically, the study examines how the students interpret their engagement in relation to their Islamic background. The study aims to provide deeper understanding and greater awareness of female Muslim students’ participation in sporting activities within the public high school environment and the challenges they may face. The study employed critical race and social identity theories as an analytical framework. In addition, the study utilized qualitative research methods. Semi-structured interviews were conducted with 11 female Muslim students and 4 teachers responsible for sporting activities in school. The findings of the study reveal that despite a variety of sporting activities provided by Australian public high schools, some of these activities were challenging for Muslim girls to participate in. The study also found that there is a strong relationship between students’ Islamic background and their participation in schools sporting activities. The study recommends that educators and teachers who work with youth from different background are provided training on equity issues arising from ethnicity, race, culture, religion and other identity categories.     

Crisis of Natural Building Materials and Institutionalised Self-Help Housing: The Case of Grameen Bank in Bangladesh

Traditional rural housing is largely based on the use of locally available natural resources as prime building materials, usually in a process of self-help building undertaken by the community. Such housing is well adapted to a natural environment with widely available resources, and supports people's direct involvement in the construction of their dwellings. However, the advent of a cash economy and current scarcity of natural resources has greatly affected the self-help building process. In rural Bangladesh, affluent households are shifting to manufactured materials and skilled builders, and the quality of housing of low-income households is declining. For the latter, self-help is the only option, and recognition of this fact and of the increasing decline in the quality of their housing has prompted institutional intervention. This paper discusses the Grameen Bank's rural housing programme in Bangladesh which provides loans for manufactured building components for low-income rural households to build houses on a self-help basis. A review of this programme indicates some of its strengths and shortcomings in the context of scarcity of natural building materials and widespread poverty.     

Effects of some design factors on the distribution of similarity indices in cluster analysis

This article investigates the effects of number of clusters, cluster size, and correction for chance agreement on the distribution of two similarity indices, namely, Jaccard and Rand indices. Skewness and kurtosis are calculated for the two indices and their corrected forms then compared with those of the normal distribution. Three clustering algorithms are implemented: complete linkage, Ward, and K-means. Data were randomly generated from bivariate normal distributions with specified means and variance covariance matrices. Three-way ANOVA is performed to assess the significance of the design factors using skewness and kurtosis of the indices as responses. Test statistics for testing skewness and kurtosis and observed power are calculated. Simulation results showed that independent of the clustering algorithms or the similarity indices used, the interaction effect cluster size x number of clusters and the main effects of cluster size and number of clusters were found always significant for skewness and kurtosis. The three way interaction of cluster size x correction x number of clusters was significant for skewness of Rand and Jaccard indices using all clustering algorithms, but was not significant using Ward's method for both Rand and Jaccard indices, while significant for Jaccard only using complete linkage and K-means algorithms. The correction for chance agreement was significant for skewness and kurtosis using Rand and Jaccard indices when complete linkage method is used. Hence, such design factors must be taken into consideration when studying distribution of such indices.     

A Note on Regression-Type Estimators Using Multiple Auxiliary Information

Kiregyera (1984), Mukerjee, Rao & Vijayan (1987), and Tripathi & Ahmed (1995) considered a number of regression-type estimators where information on two auxiliary variables related to study variable is available at different levels. Mukerjee et al . (1987) suggested three estimators and computed their mean square errors, but the computations seem to be incorrect. This note corrects them, and finds their estimators are no better than that of Kiregyera (1984). The estimator suggested by Tripathi & Ahmed (1995) is the best in the sense of having the smallest mean square error.     

Simultaneous estimation of means of two sensitive variables

In this paper, we introduce a new problem of simultaneous estimation of means of two quantitative sensitive variables by using only one randomized response another pseudo response from a respondent in a sample. The proposed estimators are extended to stratified random sampling, and the relative efficiency values are computed for equal, proportional, and optimum allocation with respect to the newly introduced naïve estimators.     

Social Work Student Views on Palliative Care Learning Resources

Abstract

Many social workers are expected to work with individuals and families who are dealing with life-limiting illnesses, yet during their university education they may not have been exposed to materials that address issues related to death and dying. The Social Work Department of University of New England in Armidale, Australia designed and delivered a palliative care teaching and learning session using publicly funded online materials. Themes emerging from questionnaire and focus group data analysis included appreciation for the importance and emotional demands of the materials, sensitivity and flexibility among educators who ideally have work experience in the field, expanding presence of social work philosophy in curriculum materials and exploring spirituality, and examining culture-informed practice in greater depth. Among the implications is the need for concerted efforts to teach about death and dying using high quality accessible materials, while ensuring social work values and approaches are reflected in the content.