Reproducibility Study: "A Framework for Analyzing the Impact of Missing Data in Predictive Models"

The aim of this paper is to investigate the reproducibility of the paper "A Framework for Analyzing the Impact of Missing Data in Predictive Models". Due to the need of a lot of computational power and long run times, the number of considered settings was reduced. After reproducing the experiment, the outcome was compared with the original paper. We were able to replicate and confirm the main finding of the original paper, which states that a larger sample size increases the accuracy, while a higher number of variables has a negative impact. However, some other effects turned out to deviate massively from the originally presented ones.