Sequential Bayesian Data Synthesis for Mediation and Regression Analysis

A Randomization Permutation Test for Single Subject Mediation

In response to the importance of individual-level effects, the purpose of this paper is to describe the new randomization permutation (RP) test for a mediation mechanism for a single subject. We extend seminal work on permutation tests for individual-level data by proposing a test for mediation for one person. The method requires random assignment to the levels of the treatment variable at each measurement occasion, and repeated measures of the mediator and outcome from one subject. If several assumptions are met, the process by which a treatment changes an outcome can be statistically evaluated for a single subject, using the permutation mediation test method and the permutation confidence interval method for residuals. A simulation study evaluated the statistical properties of the new method suggesting that at least eight repeated measures are needed to control Type I error rates and larger sample sizes are needed for power approaching .8 even for large effects. The RP mediation test is a promising method for elucidating intraindividual processes of change that may inform personalized medicine and tailoring of process-based treatments for one subject.

Modern Meta-Analytic Methods in Prevention Science: Introduction to the Special Issue

Meta-analyses that statistically synthesize evidence from multiple research studies can play an important role in advancing evidence-informed prevention science. When done in the context of a well-conducted systematic review, meta-analysis is a powerful tool for synthesizing evidence and exploring research questions that are difficult to address in individual studies, such as the association of individual study limitations on intervention effect estimates, replicability of empirical findings, and variation of effect estimates across populations and settings. Alongside the rapid growth in the number of published reviews and meta-analyses, there has been a parallel growth in the development of meta-analytic techniques to handle the increasingly complex types of questions and types of evidence relevant to prevention science. Despite this rapid evolution of meta-analytic techniques and approaches, there is still a lag between the development of new techniques and their uptake by researchers in the field. This paper serves as a brief introduction to this special issue of Prevention Science, entitled "Modern Meta-Analytic Methods in Prevention Science," which highlights recent developments in meta-analytic methods and demonstrates their application to prevention research. This special issue makes an important contribution to the field by ensuring these methodological advances are widely accessible to prevention science researchers, thereby improving their uptake and utilization, and ultimately improving the utility and rigor of research syntheses for informing evidence-based decision making in prevention.

Leveraging Research Synthesis Methods to Support Evidence-Based Policy- and Decision-Making

This commentary discusses the potential utility of research syntheses for evidence-based policy- and decision-making, examining the papers that comprise the special issue on modern meta-analytic methods. Evidence and data have the potential to play a critical role in the development of policies and in the administration of programs that meet the social and economic needs of children and families. Novel, innovative, and methodologically rigorous methods that allow for comprehensive and systematic research synthesis, such as those disseminated in this special issue, can help inform the work of the federal government and the prevention science field at large. Overall, the papers hold promise for strengthening the rigor of existing approaches, illustrate novel approaches, and demonstrate the utility of information that research syntheses can produce. Collectively, the studies in this special issue advance the available toolbox of methods that can be used to support evidence-based policy- and decision-making.

Next-Generation Meta-analysis for Next-Generation Questions: Introducing the Prevention Science Special Issue on Modern Meta-analytic Methods

This commentary accompanies the special issue of Prevention Science on modern meta-analytic methods. The papers that comprise this special issue are considered in terms of the next-generation meta-analytic questions they support: questions about multivariate relationships, drawing on real-life data structures, with improved usability, and answered openly. The contributions to this special issue illustrate a range of methods to address these questions, including meta-analytic structural equation modelling; robust variance estimation and network meta-analysis methods; transportability and causal inference; Bayesian methods; and open science. This special issue collectively represents a step forward in the field's ability to address questions of use to improving human welfare through preventing ill health, supporting uptake of these next-generation methods by applied researchers in prevention science. Future methodological developments in meta-analysis should be synergistic with the questions prevention scientists seek to answer, both creating new possibilities and meeting the challenges of improving human health and wellbeing.