Hazard ratio inference in stratified clinical trials with time‐to‐event endpoints and limited sample size

The stratified Cox model is commonly used for stratified clinical trials with time‐to‐event endpoints. The estimated log hazard ratio is approximately a weighted average of corresponding stratum‐specific Cox model estimates using inverse‐variance weights; the latter are optimal only under the (often implausible) assumption of a constant hazard ratio across strata. Focusing on trials with limited sample sizes (50‐200 subjects per treatment), we propose an alternative approach in which stratum‐specific estimates are obtained using a refined generalized logrank (RGLR) approach and then combined using either sample size or minimum risk weights for overall inference. Our proposal extends the work of Mehrotra et al, to incorporate the RGLR statistic, which outperforms the Cox model in the setting of proportional hazards and small samples. This work also entails development of a remarkably accurate plug‐in formula for the variance of RGLR‐based estimated log hazard ratios. We demonstrate using simulations that our proposed two‐step RGLR analysis delivers notably better results through smaller estimation bias and mean squared error and larger power than the stratified Cox model analysis when there is a treatment‐by‐stratum interaction, with similar performance when there is no interaction. Additionally, our method controls the type I error rate while the stratified Cox model does not in small samples. We illustrate our method using data from a clinical trial comparing two treatments for colon cancer.     

Does the Risk Outweigh the Benefits? Adolescent Responses to Completing Health Surveys

The aim of this study is to describe the self‐reported experiences of adolescents in population‐based samples when completing health‐related surveys on topics with varying potential for evoking distress. Survey data were collected in three school‐based studies of bullying behaviors (N = 1,771, 12–14 years), alcohol use (N = 823, 12, 15, and 17 years), and electronic image sharing (N = 274, 13 years). Between 5% and 15% of respondents reported being upset at survey completion, but at most 1.4% were entirely negative in their evaluation. Age was not associated with being upset, but younger adolescents were more likely to see benefit in participation. Although concurrent mental health symptoms increased the risk of being upset, this was mostly mitigated by perceived benefits from participation.     

Addressing the cultural complexity of OHS in the Australian mining industry

This paper summarises the findings of the site assessments of ten pilot mine sites involved in a project entitled, Creating a world-leading OHS culture in the NSW Mining Industry which was undertaken for the New South Wales Mine Safety Advisory Council (NSW MSAC). NSW MSAC was established in 1998 in NSW Australia and aims to increase the emphasis on safety and health within the mining industry by reviewing and analyzing safety performance, setting strategic directions, providing advice and developing policy recommendations. The project itself aimed to deliver a self-sustaining method for achieving and monitoring continuous improvement in OHS culture and practice to the NSW mining industry. The pilot sites involved in the project tested a set of self-assessment tools to enable mines to assess and improve their own OHS culture and performance on key elements of an OHS management system. The tools allowed examination of the current OHS culture of the sites. Sites then used a participative planning process to develop an improvement plan. This paper provides summary data only, without identifying the individual sites that were the source of the data.     

Science and social work: a sketch

While recognizing that understanding of ‘science’ varies across time and countries, there are strands of a shared albeit diverse inheritance. Failures to see where we are located within this inheritance make the social work community vulnerable to simplistic claims regarding what, for example, ‘doing science’ is like. This in turn makes it difficult to deal adequately with questions such as in what ways can or should we distinguish social work science from other kinds of knowledge? Is science in some recognizable way a unified form of knowledge? How ought we to deal with disputes and disagreements in social work science? What kinds of consequences might we envisage from social work science? I deal in turn with each of these questions.     

Sociological social work: a cartoon

I trace an account of social work—and sociology—that I believe holds a promise for re-forming the relationship between the two. I develop the argument in two ways. First, taking 1920s Chicago as a case study, I will attempt ‘a history of the present’ to suggest how the relationship between sociology and social work came to be as it is. I will suggest that the practice of some (both familiar and forgotten) people in 1920s and 1930s sociology and social work is best explained as a form of ‘sociological social work’. Second, after tracking this genealogy, I suggest an agenda for sociological social work that consists of straining to enact certain kinds of inter-disciplinary relationships, developing methodological social work practice, hearing occasional sociological frontier conversations and shared theorising. I illustrate how these arguments challenge both sociology and social work and both theory and practice.