Comparing methods addressing multi-collinearity when developing prediction models

TL;DR

This paper compares various statistical methods like shrinkage, dimensionality reduction, and constrained optimization to handle multicollinearity in clinical prediction models, highlighting their effects on predictor stability through simulations.

Contribution

It provides a systematic comparison of methods addressing multicollinearity in prediction models, emphasizing their impact on predictor stability rather than predictive accuracy.

Findings

No effect of collinearity on predictive outcomes in simulations

Collinearity negatively affects predictor stability across methods

Strong predictor selection methods are more impacted by collinearity

Abstract

Clinical prediction models are developed widely across medical disciplines. 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. Collinearity can be dealt with by exclusion of collinear predictors, but when there is no a priori motivation (besides collinearity) to include or exclude specific predictors, such an approach is arbitrary and possibly inappropriate. We compare different methods to address collinearity, including shrinkage, dimensionality reduction, and constrained optimization. The effectiveness of these methods is illustrated via simulations. In the conducted simulations, no effect of collinearity was observed on predictive outcomes. However, a negative effect of collinearity on the stability of predictor selection was found, affecting all compared methods, but in particular methods that perform strong predictor selection (e.g., Lasso).}