University of Bristol

Academic Institute

B3708

Often a large number of equally plausible possible analysis options are available to researchers. Multiverse analysis is a proposed way of overcoming this problem where all plausible analyses are conducted and the results of all are interpreted in the context of each other. This information can be used as a measure of the reliability of a result, which in turn is useful for scientific advancement and deciding policy. However, multiverse analysis can be time consuming and complex. This project will use ALSPAC data to test and inform the building of an R/python package to conduct multiverse analysis, which is currently being built. This package will make multiverse analysis easier to conduct, encouraging greater adoption of this technique across the health sciences.

This research will contribute to the creation of an analysis package which will help make multiverse analysis easier to conduct, encouraging greater adoption of this technique across the health sciences.

01/02/2021