A Split of a Country - A Bayesian Net Approach to the Study of Complex Political Events

In this paper, we will aim to show the application of Bayesian Nets to the study of a major political event and its consequences. The selected event is the Scottish Independence Referendum in 2014. The power of Bayesian Nets allows to extend the cognitive depth of the analysis compared to what humans can achieve through lengthy economic narratives, as it is based on causal graphical reasoning made consistent through probability theory. The calibration of the model is made on expert, historical and market implied information. We perform some sensitivity analyses to check the robustness of the results. The approach described in this paper is applicable to the analysis of any complex political event (e.g. Brexit) beyond the simple case study presented herein