Me and Yves Plessen from Charité had the pleasure of co-moderating a session on publication bias and questionable research practice methods at the 2023 ESMARConf. You can find the recording below.
Summary
The goal of systematic reviews and meta-analyses is to provide a comprehensive, unbiased synthesis of the available evidence in a research field. This aim is seriously threatened if we have reasons to believe that some results are systematically missing, underrepresented or distorted in the published literature.
Controlling adequately for such publication biases in meta-analyses remains challenging. Various methods are available, which differ in their assumptions concerning why publication bias arises, as well as how it manifests itself.
Bringing together highly experienced field experts, the goal of this panel discussion is to highlight current state-of-the-art methods to control for publication bias, and their implementations in R. We also want to shed light on how evidence synthesists may navigate the great variety of approaches and implementations, and if some may be preferable to others. Finally, we aim to explore open research questions and future directions in the development of methods to adjust for publication bias.