E Riccomagno, JQ Smith and P Thwaites
Algebraic discrete causal models
Abstract: The main feature of the paper is to show that Algebraic Statistics is a natural framework to address issues of causality and to help discern a total cause. Indeed identifiability of an effect of a cause in discrete models is almost algebraic rather than graphical in nature. It is useful to think of it as such and it leads to the definition of a large class of discrete models which comprises popular ones.
Keywords: Causality, Algebraic Statistics, Identifiability.