AUTHOR=Temp Anna G. M. , Naumann Marcel , Hermann Andreas , Glaß Hannes 

TITLE=Applied Bayesian Approaches for Research in Motor Neuron Disease

JOURNAL=Frontiers in Neurology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2022.796777

DOI=10.3389/fneur.2022.796777

ISSN=1664-2295

ABSTRACT=Statistical evaluation of data is the basis of the modern scientific method. Albeit the importance of statistics is pivotal many misconceptions arise due to their complexity and difficult to understand mathematical background. While until now most studies rely on a frequentist interpretation of statistical readouts, with the advent of sufficient computational capacities Bayesian statistics have become feasible as well. This theory uses our prior knowledge to express a degree of belief how likely a certain event is. Bayes factor hypothesis testing (BFHT) provides a straightforward method to evaluate multiple hypotheses at the same time and provides evidence that favours the null- hypothesis or alternative hypothesis instead of merely rejecting a null-hypothesis. In the present study we applied BFHT to synthetic data based on Biogen’s phase I/II trial of tofersen showing that the data does not favour neither the hypothesis of a positive treatment effect nor the hypothesis of no treatment effect. Similarly, we re-analysed our previously published data on DNA damage in a cell culture model of ALS and found evidence for a strong effect of the FUS p.P525L mutation on the susceptibility to DNA damage, which could have not been detected previously. Lastly, we show a potential application of BFHT with Monte Carlo sampling in a single case study to compare an index patient to a healthy control population. Here we show that Bayesian statistics is a viable addition a scientist’s statistics toolset, which can help to interpret data.