Aggregation methods and comparative study in time-to-event analysis models

Time-to-event analysis is a branch of statistics that has increased in popularity during the last decades due to its many application fields, such as predictive maintenance, customer churn prediction and population lifetime estimation. Our main contribution is to offer a deep understanding of the interactions between model assumptions and dataset characteristics, along with the effectiveness of different scoring metrics in assessing predictive accuracy and robustness. To this end, we review and compare the performance of several prediction models for time-to-event analysis. These consist of semi-parametric and parametric statistical models, in addition to machine learning approaches. Our study is carried out on four datasets and evaluated in two different scores (the integrated Brier score and concordance index). Moreover, we show how aggregation methods can improve the prediction accuracy and enhance the robustness of the prediction performance. We conclude the analysis with a simulation experiment in which we evaluate the factors influencing the performance ranking of the methods using both scores.