4. Advanced methods in (Network) Meta-Analysis – A Practical Course in R

Detailed course information (PDF)

Faculty

Prof. Georgia Salanti
Institute of Social and Preventive Medicine (ISPM), University of Bern, Switzerland

Dr. Guido Schwarzer
Institute for Medical Biometry and Statistics (IMBI), University of Freiburg, Germany

Introduction

Standard meta-analysis methods for clinical and epidemiological studies are widely used with focus on comparisons of two interventions, such as a drug versus a placebo, or a new intervention versus standard practice. However, contemporary research questions require methods that are beyond the state-of the art. Investigators often need to synthesized data that are potentially subject to publication bias, several health outcomes or need to compare more than two interventions for the same condition. Extensions of meta-analysis methods to address these aims have been the subject of much methodological research in recent years, and are increasingly being applied. This course will explain the theory and application of meta-regression models, methods to investigate the risk of publication bias, multivariate meta-analysis, and network meta-analysis.

This course is aimed at statisticians, epidemiologists and other quantitatively-minded researchers who want to understand and undertake beyond-the-standard statistical syntheses of clinical trials. Knowledge of systematic reviews and the fundamentals of meta-analysis is expected of all participants. Participants must be statistically literate, including a good understanding of linear regression, meta-analysis, random-effects models and matrices. Computer practicals will use R packages requiring basic experience with R software.

Course objectives

By the end of this short course participants will have an understanding of:

  • The role and potential of meta-regression, multivariate meta-analysis and network meta-analysis; the potential and limitations of methods to detect and account for small-study effects; methods to infer about the risk of publication bias
  • The principles, steps and statistical methods involved.

Participants will gain practical experience in performing analyses in R.

Course fees

Academic fee: CHF 900
Industry fee: CHF 2’000
SSPH+ fee: only applicable for students of the SSPH+ PhD Program in Public Health