Analyzing the impacts of socio-economic factors on French departmental elections with CODA methods

The proportions of votes by party on a given subdivision of a territory form a vector called composition (mathematically, a vector belonging to a simplex). It is interesting to model these proportions and study the impact of the characteristics of the territorial units on the outcome of the elections. In the political economy literature, such regression models are generally restricted to the case of two political parties. In the statistical literature, there are regression models adapted to share vectors including CODA models (for COmpositional Data Analysis), but also Dirichlet models, Student models and others. Our goal is to use CODA regression models to generalize political economy models to more than two parties. The models are _tted on French electoral data of the 2015 departmental elections.