Thomas Debray is an assistant professor experienced in statistical methods for prediction modeling research using large, clustered, datasets from e-health records or individual participant data meta-analysis. His work primarily relates to assessing and improving the generalizability of risk predictions, to which purpose he refines methods for validation, regression analysis and machine learning. Many of these extensions have been implemented in his R package "metamisc", hosted on CRAN (https://CRAN.R-project.org/package=metamisc)
Thomas is currently appointed at Oxford University, University College London and Cochrane Netherlands where he provides guidance on the implementation of advanced meta-analysis methods.
- VENI - ZonMW NWO - Better predictions using big data sets - Grant number: 016.176.050