Causal attribution in block-recursive social systems: A structural modeling perspective

• Published in: Methodological innovations 2018, Vol.11 (1), p.1
• Main Authors: Wunsch, Guillaume, Mouchart, Michel, Russo, Federica
• Format: Article
• Language: English
• Subjects: Attribution; Causality; Decomposition; Interdisciplinary aspects; Population; Social sciences; Social systems; Structural models; Variables
• ISSN: 2059-7991; 1748-0612; 2059-7991; 1748-0612
• DOI: 10.1177/2059799118768415

One method for causal analysis in the social sciences is structural modeling. Structural models, as used in this article, model the (causal) mechanism for a social phenomenon by recursively decomposing the multivariate distribution of the variables of interest. Often, however, one does not achieve a complete decomposition in terms of single variables but in terms of “blocks” of variables only. Papers giving an overview of this issue are nevertheless rare. The purpose of this article is to categorize distinct types of block-recursivity and to examine, in a multidisciplinary perspective, the implications of block-recursivity for causal attribution. A probabilistic approach to causality is first developed in the framework of a structural model. The article then examines block-recursivity due to the presence of contingent conditions, of interaction, and of conjunctive causes. It also discusses causal attribution when information on the ordering of the variables is incomplete. The article concludes by emphasizing, in particular, the importance of properly specifying the population of reference.