This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Causality in Economics & Stephen F. LeRoy University of California, Santa Barbara October 3, 2006 The initiation of quantitative analysis of formal structural models in the social sciences is generally attributed to the Cowles Commission economists in the 1950s (see Hood and Koopmans  for a collection of some of the most important pa- pers). Since then the new methods have been extended and re&ned and applied in the other social sciences. Graphical methods based on the Cowles developments are increasingly used in the social and biological sciences. The theme of this paper is that recent purported re&nements of the Cowles analysis, particularly as it relates to representations of causal relations in formal models, departed from the Cowles analy- sis to a greater extent than is commonly realized. The suggestion is that the Cowles development as interpreted here compares favorably to more recent developments. 1 Causation The term ¡structural¢was given several distinct, though related, meanings by the Cowles economists, as has frequently been observed. At a minimum, the term refers to the distinction between the structural form and the reduced form of a model. In the structural form each internal variable is expressed as a function of some other internal variables and some external variables, whereas the reduced form referred to the solution of a model, in which each internal variable is expressed as a function of the external variables alone. As the term implies, the structural form was viewed as more fundamental than the reduced form. It was seen as containing information not present in the reduced form, such as exclusion restrictions. For example, a structural supply-demand system might specify that one or several of the external variables a/ect demand but not supply, or vice-versa. These restrictions were used to identify structural coe£ cients. A second meaning of ¡structural¢, one more basic than that discussed above, has to do with invariance under intervention. The Cowles economists implicitly dis- tinguished two classes of hypothetical experiments: (1) determining the e/ects of & First draft August 25, 1999. I have received helpful comments from Nancy Cartwright, Daniel Hausman, Damien Fennell, Julian Reiss and two referees.. 1 routine realizations of external variables, and (2) analyzing changes in model struc- ture. There is no formal justi&cation for this distinction since hypothetical model shifts can always be parametrized, allowing the analyst to represent an intervention on the structure of a model via a hypothetical shift in an external variable. Thus in a model that is structural in this sense coe¢ cients can be treated as if they were external variables: an intervention on one or several model coe¢ cients by de&nition leaves other coe¢ cients unchanged. The Cowles economists were often unclear as to when they were treating coe¢ cients as external variables and when they were treating them as constants....
View Full Document
- Fall '08
- Economics, Causality, external variables, coe¢ cients