Vinícius Litvinoff Justus

This work is an effort towards the goal of understanding the connection between the concepts of causality and statistical dependence. Formally, this was done employing the notions of copula function and structural causal model. To achieve such goals, this dissertation first presented some problems that may arise in the analysis of non-experimental data and then presented the concepts of copula function and structural causal model. Within this context, this dissertation presented two contributions: first, based on the concept of structural equation, a copula-based procedure to control omission variable bias in linear models was presented (which is an extension of a method already present in the literature in the case of a Gaussian copula). Finally, the main contribution of this dissertation was done through representation theorems that enables seeing the impact of a causal intervention in a joint density probability function through a copula function. It was proved that the change in the joint density induced by the causal intervention is fully characterized by a copula function.