Short report: Understanding the process of multilevel suicide prevention research trials

This paper reviews process evaluations associated with multilevel suicide prevention research trials. Process evaluations can provide important information about how multilevel suicide prevention models are implemented, their mechanisms of impact, and the context and elements of implementation that mediate effectiveness. Out of 42 papers identified, only four met selection criteria for including a process evaluation. Of these four, there was large variation in the level of detail provided, and only two studies specifically focused on the process of implementing a multilevelsuicide prevention model. Future trials should include targeted process evaluation, which can benefit a range of knowledge users.     

An improved randomized response model: estimation of mean

In this paper, we suggest a new randomized response model useful for collecting information on quantitative sensitive variables such as drug use and income. The resultant estimator has been found to be better than the usual additive randomized response model. An interesting feature of the proposed model is that it is free from the known parameters of the scrambling variable unlike the additive model due to Himmelfarb and Edgell [S. Himmelfarb and S.E. Edgell, Additive constant model: a randomized response technique for eliminating evasiveness to quantitative response questions, Psychol. Bull. 87(1980), 525–530]. Relative efficiency of the proposed model has also been studied with the corresponding competitors. At the end, an application of the proposed model has been discussed.     

Social Service Research and Religion

Abstract

Development of accountability standards to demonstrate cause and effect relationships are gaining rapid advancement in the field of social sciences. Many governmental agencies, foundations, and other funders have developed approaches that require organizations to utilize science-based programs and incorporate evaluative methods to show improved outcomes and cost benefits to society. This article will examine the need for increased accountability in developing effective interventions by faith-based organizations in the delivery of social service interventions. Recently, there has been a strong movement toward governmental funding for faith-based institutions to provide social services, although there has been inadequate scientific data to demonstrate that approaches implemented are effective in meeting needs or yielding favorable outcomes. Similarly, many faith-based organizations provide innovative and effective programs that could serve as model programs if there was appropriate empirical evidence. This article will discuss how rigorous evaluative approaches such as randomized clinical control trials can produce scientific data on program effectiveness. We will use a case example in the field of drug and alcohol treatment to illustrate these points.     

Semiparametric estimation and inference for distributional and general treatment effects

Summary.  There is a large literature on methods of analysis for randomized trials with noncompliance which focuses on the effect of treatment on the average outcome. The paper considers evaluating the effect of treatment on the entire distribution and general functions of this effect. For distributional treatment effects, fully non-parametric and fully parametric approaches have been proposed. The fully non-parametric approach could be inefficient but the fully parametric approach is not robust to the violation of distribution assumptions. We develop a semiparametric instrumental variable method based on the empirical likelihood approach. Our method can be applied to general outcomes and general functions of outcome distributions and allows us to predict a subject's latent compliance class on the basis of an observed outcome value in observed assignment and treatment received groups. Asymptotic results for the estimators and likelihood ratio statistic are derived. A simulation study shows that our estimators of various treatment effects are substantially more efficient than the currently used fully non-parametric estimators. The method is illustrated by an analysis of data from a randomized trial of an encouragement intervention to improve adherence to prescribed depression treatments among depressed elderly patients in primary care practices.     

SPIRIT: A seamless phase I/II randomized design for immunotherapy trials

Immunotherapy—treatments that enlist the immune system to battle tumors—has received widespread attention in cancer research. Due to its unique features and mechanisms for treating cancer, immunotherapy requires novel clinical trial designs. We propose a Bayesian seamless phase I/II randomized design for immunotherapy trials (SPIRIT) to find the optimal biological dose (OBD) defined in terms of the restricted mean survival time. We jointly model progression‐free survival and the immune response. Progression‐free survival is used as the primary endpoint to determine the OBD, and the immune response is used as an ancillary endpoint to quickly screen out futile doses. Toxicity is monitored throughout the trial. The design consists of two seamlessly connected stages. The first stage identifies a set of safe doses. The second stage adaptively randomizes patients to the safe doses identified and uses their progression‐free survival and immune response to find the OBD. The simulation study shows that the SPIRIT has desirable operating characteristics and outperforms the conventional design.     

Efficacy of newer medications for lower urinary tract symptoms attributed to benign prostatic hyperplasia: a systematic review

We conducted a systematic review to evaluate the efficacy and adverse effects of newer drugs used to treat lower urinary tract symptoms (LUTS). The drugs were either Food and Drug Administration (FDA) approved for benign prostatic hyperplasia (BPH) or not FDA approved for BPH but have been evaluated for treatment of BPH since 2008. We searched bibliographic databases through September 2017. We included randomized controlled trials (RCTs) lasting one month or longer published in English. Outcomes of interest were LUTS assessed by validated measures. Efficacy was interpreted using established thresholds indicating clinical significance that identified the minimal detectable difference. Twenty-three unique, generally short-term, RCTs evaluating over 9000 participants were identified. Alpha-blocker silodosin and phosphodiesterase type 5 inhibitor tadalafil were more effective than placebo in improving LUTS (moderate strength evidence) but these drugs had more adverse effects, including abnormal ejaculation (silodosin). Anticholinergics were only effective versus placebo when combined with an alpha-blocker. Evidence was generally low strength or insufficient for other drugs. Evidence was insufficient to assess long-term efficacy, prevention of symptom progression, need for surgical intervention, or long-term adverse effects. Longer trials are needed to assess the effect of these therapies on response rates using established minimal detectable difference thresholds, disease progression, and harms.     

Subject‐level matching for imbalance in cluster randomized trials with a small number of clusters

In a cluster randomized controlled trial (RCT), the number of randomized units is typically considerably smaller than in trials where the unit of randomization is the patient. If the number of randomized clusters is small, there is a reasonable chance of baseline imbalance between the experimental and control groups. This imbalance threatens the validity of inferences regarding post‐treatment intervention effects unless an appropriate statistical adjustment is used. Here, we consider application of the propensity score adjustment for cluster RCTs. For the purpose of illustration, we apply the propensity adjustment to a cluster RCT that evaluated an intervention to reduce suicidal ideation and depression. This approach to adjusting imbalance had considerable bearing on the interpretation of results. A simulation study demonstrates that the propensity adjustment reduced well over 90% of the bias seen in unadjusted models for the specifications examined. Copyright © 2013 John Wiley & Sons, Ltd.     

N the theory of randomized responses to two sensitive questions

This paper sets forth a stochastic model which can be applied to randomized response designs wherein more than one question is sensitive of stigmatizing. Using three specific designs applied to a pair of stigmatizing or sensitive traits leading to two by two contingency tables, it is proved that if the two traits are statistically independent then the responses are also and conversely. The converse statement gives the support we need for inference to be made on the traits based on the randomized responses.     

The Legal Trial And/In Documentary Film

This article proposes to extend the work of law and film scholars, such as Carol Clover and Jennifer Mnookin, by looking at how juridically themed documentary films use the legal trial as both a platform and a structuring device to contest the evidentiary value of testimony, bear witness to the performance of law in our culture and engage in a social debate about flaws in contemporary jurisprudence. Because non-fiction film – with its presumed indexical relationship to reality and its attendant claims to authenticity – is often seen as having a privileged relationship to truth, the ethical and epistemological stakes of these visual representations are heightened. Consequently, the expectations we bring to the juridical documentary (in terms of its truth-telling responsibilities) make it a particularly loaded space for analysing the ethical and epistemological responsibilities of documentary representation as well as for revealing truths about the legal process and the ordering of a just society. Thinking through the ways in which contemporary trial documentaries differently approach the question of their subjects' guilt allows us to reflect on how the juridical documentary refracts the legal trial's own truth claims. These documentary films demonstrate that, while the documentary and the legal trial might share an epistemological affinity based on shared principles of evidence, narrative and argument, the way in which the trial itself is thematized as both a discourse and a practical purveyor of justice in documentary influences how we come to understand the law in action.     

Conditional Gaussian mixture modelling for dietary pattern analysis

Summary.  Free-living individuals have multifaceted diets and consume foods in numerous combinations. In epidemiological studies it is desirable to characterize individual diets not only in terms of the quantity of individual dietary components but also in terms of dietary patterns. We describe the conditional Gaussian mixture model for dietary pattern analysis and show how it can be adapted to take account of important characteristics of self-reported dietary data. We illustrate this approach with an analysis of the 2000–2001 National Diet and Nutrition Survey of adults. The results strongly favoured a mixture model solution allowing clusters to vary in shape and size, over the standard approach that has been used previously to find dietary patterns.