Comparing methods addressing multi-collinearity when developing prediction models

1 code implementation • 5 Jan 2021 • Artuur M. Leeuwenberg, Maarten van Smeden, Johannes A. Langendijk, Arjen van der Schaaf, Murielle E. Mauer, Karel G. M. Moons, Johannes B. Reitsma, Ewoud Schuit

When predictors in such models are highly collinear, unexpected or spurious predictor-outcome associations may occur, thereby potentially reducing face-validity and explainability of the prediction model.

Dimensionality Reduction Methodology 60 G.3