This course offers an advanced treatment of design issues in social science research that aims at causal inference, that is, at answering cause-and-effect questions of the general form: is a variable D a cause of an outcome Y? If so, how large is the effect of D on Y? And how do changes in D translate into changes in Y? Starting from an exposition of the counterfactual model of causality and causal graphs, the course introduces the assumptions necessary for identifying various causal effects, and shows to what extent these assumptions are justified in different experimental and observational research designs.
As to observational studies, the course gives an overview of common and new large-N methods for causal inference, such as regression and panel estimators, matching, instrumental variable and regression discontinuity approaches. The course also discusses how the principles and methods introduced may be put to use in small-N settings and in studies which aim to parse the mechanisms underlying causal effects.
The course’s primary aim is to provide students with the epistemological and methodological tools to critically evaluate existing empirical studies, to understand their inferential weaknesses, and to develop research designs on their own that, to the greatest possible extent, strengthen the causal inferences made.
The course takes place on Thursdays 11.45-13.15 in D432, the accompanying tutorial on Mondays 11.45-13.15 in C421.