UCL JILL DANDO INSTITUTE OF SECURITY AND CRIME SCIENCE

Jill Dando Institute of Crime Science

• Home Page
• About Us
• People
• Postgraduate Taught Programmes
• Short Courses
• Research
• PhD Training - UCL SECReT
• JDI Centre for the Forensic Sciences
• Events
• Contact Us

Statistical modelling and causality

We tackle causality from an epistemological and methodological perspective. Here, we address the question of how we come to accept causal relations by means of statistical models. In our view of moderate scientific realism, models are not the locus of final truth but they can give at least partial and approximate knowledge of external realities and their interrelations. The selection of relevant data surely is a crucial step in scientific knowledge-building, although it stays highly problematic. We consider a statistical model to be a stochastic representation of the world – its randomness delineates the frontiers or the internal limitation of statistical explanation. More specifically, we analyze conditional statistical models. Such models are also called structural – this conveys the idea of a representation of the world that is stable over a large class interventions. To uncover the structural aspect of a causal system it is customary to operate a marginal-conditional decomposition of the statistical model, and we define a causal variable to be an exogenous variable in a structural conditional model. However, exogeneity only provides an operational concept of causality. A more complex and rich concept of causality can be worked out once we consider the fundamental role of assumptions, of background knowledge and of the hypothetico-deductive methodology. (Joint work: Federica Russo, Michel Mouchart, Michel Ghins, Guillaume Wunsch).

Speaker

Federica Russo is research associate at the University of Kent (Canterbury), where she's working on a project on causality and probability in the social and health sciences with Jon Williamson. She completed her PhD on causal modelling in the social sciences at the University of Louvain (Belgium) in June 2005. She graduated from the University of Padua with a dissertation on causal explanation, and obtained a DEA (MSc) in Philosophy of Science from the University of Louvain. Federica has visited the Centre for Philosophy of Natural and Social Science (CPNSS) at the LSE (April 2004 - January 2005).