Interactive figure from "The multiplicity of analysis strategies jeopardizes replicability: lessons learned across disciplines (2021)"

Figure 4 - Overview of solutions to the replication crisis which address the multiplicity of analysis strategies by reducing, reporting, integrating or accepting uncertainty. Click the text in the map below to view further references.

Click here to access the paper
Report Uncertainty Sensitivity Analysis Intercomparison Studies Multimodel Ensembles Crowdsourcing Vibration of Effects Multiverse Analysis Multimodel Analysis Specification Curve Computational Robustness Analysis Reduce Uncertainty Benchmarking Studies Increase Sample Size Integrate Existing Knowledge More Precise Theories Standardize Experimental Conditions Improve Measurements Accept Uncertainty Multiple Lines of Evidence Distinguish Explanatory and Confirmatory Analyses Meta-Analysis Acknowledge Constraints on Generality Replication Studies Move to p<0.005 Integrate Model Uncertainty Multiple Lines of Evidence Multimodel Inference Method Uncertainty Super Learner Parameter Uncertainty Probabilistic Sensitivity Analysis Bayesian Deep Learning Measurement Uncertainty Structural Equation Modeling Simulation Extrapolation Regression Calibration Bayesian Hierarchical Modeling

Authors: Sabine Hoffmann, Felix Schönbrodt, Ralf Elsas, Rory Wilson, Ulrich Strasser and Anne-Laure Boulesteix

To report a broken link, please contact Dr. Sabine Hoffmann at shoffmann@ibe.med.uni-muenchen.de