Prediction model for rare events in longitudinal follow-up and resampling methods

Abstract

We consider the problem of model building for rare events prediction in longitudinal follow-up studies. In this paper, we compare several resampling methods to improve standard regression models on a real life example. We evaluate the effect of the sampling rate on the predictive performances of the models. To evaluate the predictive performance of a longitudinal model, we consider a validation technique that takes into account time and corresponds to the actual use in real life.