Advanced meta-analysis techniques for synthesizing data from animal studies

Course description

During this advanced workshop, participants will delve into the practicalities of conducting advanced meta-analytic techniques suitable for synthesising data from animal studies, namely multi-level meta-analysis and individual animal analysis. Prior to attending this workshop, we recommend first-hand experience conducting meta-analysis of animal studies, as well as intermediate experience with R, see meta-analysis tutorial web-application for more information. 

Learning objectives

Participants will:

• gain a solid understanding of the theoretical foundations of multi-level models, including the differences between clustered data, fixed effects, and random effects. 
• learn to use R packages to implement multi-level models, interpret the output, and compare the results with naïve non-multi-level regression models. 
• explore options for handling missing data in meta-analysis, including using multi-level models and multiple imputation techniques. 
• be introduced to individual animal data (IAD) meta-analysis, learning both two-stage and single-stage analysis methods, with practical exercises using R.
• delve into advanced methods for handling missing data in IAD situations, including multiple imputation and advanced models for data that are not missing at random (non-MAR).

Target audience

BIH, CHA, BUA, external, research fellows, PhDs, students - all scientists working with meta-analysis of animal data.

Participation requirements

Prior to attending this workshop, we recommend first-hand experience conducting meta-analysis of animal studies, as well as intermediate experience with R, see meta-analysis tutorial web-application for more information. 

Lecturers

Alexandra Bannach-Brown, PhD, BIH QUEST Center

Dr. Daniel Schulze, Institut für Biometrie und Klinische Epidemiologie