This paper aims to extend the framework of causal modelling to teleological explanations. It conceives final models as second-order models produced by interventions on first-order causal models. It shows why such formalisation permits us to realise a finalistic interpretation of statistical correlation which is compatible with its usual causal interpretation. Initially, the paper identifies some conceptual conditions for statistical teleological analysis, specifically involving interventions. Then, it describes an explanation procedure for action and presents one simple example of identifiable final models. Finally, it compares these results with what could be obtained within a purely causalist framework.