Course overview

Systematically synthesizing studies stands as a critical element in advancing knowledge and facilitating informed decision-making in public health practice, policy, and research. One important way to synthesize evidence is through meta-analysis. Meta-analysis is a statistical toolkit used to consolidate findings from multiple primary studies, allowing for a robust estimation of the pooled effect size and to assess the quantitative heterogeneity across available estimates. Thus, in this workshop, participants will learn how to conduct meta-analysis and interpret their results. 

Particular emphasis will be placed on meta-analytic methods to pool the quantitative evidence available, describing the different types of models available and how to assess quantitative heterogeneity (ie. variability of intervention effects across studies) including specific test of homogeneity, outlier detection and meta-regression analysis. We will also examine methods to assess small studies effects, publication bias, and sensitivity analyses. We will learn how to interpret and report meta-analysis results including forest plots and graphical ways to detect small-study effects (publication bias). A basic introduction to the freely available software R will also be provided and used to perform meta-analysis and meta-regressions.

• Evidence everywhere – introduction

• Study Designs

• Randomized Controlled Trials

• Observational studies (cohort, case-control, cross-sectional) 

• Critical appraisal – Reporting checklists and Risk of Bias assessments 

• Systematic Reviews

• Types of Reviews

• Citation software (Zotero) 

• Some AI-based tools to improve reviews (lit-maps, scisummary, etc)

• An intro to R 

• Meta Analysis

• Methods/models of pooling 

• heterogeneity, small-study effects, meta-regression, sensitivity analyses

• A gentle introduction to Bayesian Analysis

• Bayesian Meta-Analysis

• Wrap up: Planning your review and meta-analysis, protocol development, dissemination 

By the end of this course, participants will: 

• Know the basic methods of the meta-analytic toolkit

• Be able to describe and interpret the results of meta-analysis

• Be able to perform a full meta-analysis using R 

No previous knowledge assumed.

 
Each participant should install on their laptop the freely available software R (https://cran.r-project.org)  and its graphical interface RStudio (https://posit.co/download/rstudio-desktop/) to perform hands on meta-analysis. 

Gian Luca Di Tanna is an international expert on statistical methods in randomised clinical trials and observational research, with a specific interest in Bayesian methods, evidence synthesis/meta-analysis, and their use to inform new studies and health economic evaluations. He is currently a Professor of BioStatistics & Health Economics and Head of Research of the Department of Business Economics, Health, and Social Care (DEASS) at the University of Applied Sciences and Arts of Southern Switzerland (SUPSI) and a member of the Department of Clinical Research (DCR) of the University of Bern and of the Academic Board of the Swiss School of Public Health (SSPH+)

He has honours in Statistics (2000), an MSc in Data Intelligence in Decision Analysis (2005), a post-graduate Specialization Degree (MPhil/PhD, 2003) in Medical Statistics, and a PhD in Health Economics (2012). With 23+ years of  professional experience, he has joined SUPSI after few years at the George Institute for Global Health - Faculty of Medicine, University of New South Wales, Australia where he had the role of Head of the Bio-Statistics & Data Science Division and co-Head of the Meta-Research and Evidence Synthesis Unit. Previously, he worked at the Queen Mary University of London, London School of Hygiene and Tropical Medicine, University of Birmingham, and Sapienza University of Rome.

He is past-Chair of the Statistical Methods for Health Economics and Outcome Research SIG – Special Interest Group of the ISPOR - International Society For Pharmacoeconomics Outcomes Research, in the Editorial Board of the PharmacoEconomics and BMC Medical Research Methodology and he is Statistical Consultant of the Lancet family journals. 

Actively involved in the correct use of systematic reviews and statistical methods for pooling evidence in his capacity as a Statistical Editor of Cochrane groups, he is a Chartered Statistician of the Royal Statistical Society and Accredited Statistician of the Statistical Society of Australia. 

In 2023 he was listed in the World's Top 2% Scientists ranking published by Stanford University and Clarivate Analytics.

https://scholar.google.com/citations?user=34cOet8AAAAJ&hl=en&oi=ao

Joseph Alvin Ramos Santos is a researcher/biostatistician at DEASS/SUPSI. His main area of work includes evidence synthesis, systematic reviews and meta-analyses, and Bayesian analysis. As a researcher at SUPSI, he is leading areas of work around evidence synthesis, including developing a Bayesian workflow for conducting living systematic reviews and prospective meta-analyses; analysing the scope of use of Bayesian methods in meta-analysis in biomedical research; and examining the consequences of including incorrectly analysed cluster randomised trials and stepped wedge trials in aggregate data meta-analysis. He has worked in the past for the Bio-Statistics & Data Science Division of The George Institute for Global Health in Sydney and has published over 60 journal articles including in the Cochrane Database of Systematic Reviews and JBI Evidence Synthesis.

How to apply

Click below to be taken to the application form and payment portal:

Evidence Synthesis Workshop applications