Results of several similar studies identified with a systematic literature review can be quantitatively synthesized via meta-analysis to obtain a pooled estimate on the outcome of interest and to evaluate its heterogeneity. In its basic form, a meta-analysis typically involves comparisons of two interventions for one particular endpoint, but can be expanded with multiple treatment comparisons or outcomes. This tutorial highlights and expounds upon five key and interrelated areas on meta-analysis: 1) impetus for systematic reviews and meta-analysis, 2) basic steps to perform a systematic literature review, 3) statistical methods of combining data, 4) reporting of results, and 5) appraisal and use of meta-analytic reports. In addition, network meta-analysis (indirect and mixed treatment comparisons) – and expansion of traditional meta-analysis for the same pairwise comparison – will be presented where a) its value will be discussed for coherent decision making; b) its concepts and assumptions, such as similarity and consistency, will be identified; and c) its statistical models will be described. The material throughout the tutorial is motivated and illustrated by instructive and real examples.
Dr. Joseph C. Cappelleri earned his M.S. in statistics from the City University of New York, Ph.D. in psychometrics from Cornell University, and M.P.H. in epidemiology from Harvard University. In June 1996, he joined Pfizer Inc as a statistical scientist collaborating with Outcomes Research and is an executive director of biostatistics at Pfizer. He has also served on the adjunct faculties of Brown University, Tufts Medical Center, and the University of Connecticut. Dr. Cappelleri has delivered numerous conference presentations and has published extensively (approximately 400 publications) on clinical and methodological topics, including regression-discontinuity designs, health measurement scales, and meta-analysis. He was a member of the International Society for Pharmacoeconomics and Outcomes Research (ISPOR) Task Force on Indirect Treatment Comparisons Good Research Practices. Dr. Cappelleri is an associate editor for the journal Research Synthesis Methods. Dr. Cappelleri is a Fellow of the American Statistical Association.
Dr. Din Chen is the Wallace Kuralt Distinguished Professor at the University of North Carolina-Chapel Hill. Dr. Chen is a fellow of American Statistical Association and a senior expert consultant for biopharmaceuticals and government agencies with extensive expertise in clinical trial biostatistics. Dr. Chen has more than 160 referred professional publications and co-authored/co-edited twelve books on clinical trials, interval-censored survival data analysis, meta-analysis, public health statistics, statistical causal inferences, statistical methods in big-data sciences and Monte-Carlo simulation-based statistical modeling.