Introduction to Meta-Analysis
Lecturer Jan Beyersmann
Exercises taught by Arthur Allignol
Prerequisites: The level of the course is that of a last year's bachelor course in Mathematical Biometry.
Exam: In order to be admitted to the exam, students must have made a meaningful attempt to solve at least 80% of all Problems.
Time and Venue
Lectures Monday, 12:00-14:00, HeHo 18/120
Exercises Wednesday, 13:00-14:00, HeHo 18/E20
Meta-analysis is the statistical methodology for combining quantitative evidence from different (clinical) studies. Meta-analysis is very prominent in medical research, where it features in almost every systematic review, but it is also attracting increasing interest in other fields such as economics. Major practical concerns which fuel methodological research to this day are the need to detect and adjust for possible biases such as publication bias, synthesis from studies which compared different combinations of interventions or studies that measured interventions on different scales or with different outcomes.
Meta-analysis applies to any outcome type. In this course, we will also (re-) consider the most important biometrical outcomes and their mathematical properties; these should be known by every graduate in Mathematical Biometry (BSc).
Borenstein M, Hedges LV, Higgins J, Rothstein H. Introduction to meta-analysis. Chichester, U.K.: John Wiley & Sons; 2009.
Cooper HM, Hedges LV, Valentine JC. The handbook of research synthesis and meta-analysis. New York: Russell Sage Foundation; 2009.
Lachin J, Biostatistical Methods, Wiley 2011