Graphical Models for Causal Inference with Observational Data

Instructor

felix elwertFelix Elwert is the Vilas Associate Professor of Sociology at the University of Wisconsin–Madison. He is an expert in causal inference and regularly teaches courses on the subject. He conducts substantive research on topic in social demography, social stratification, and human mortality. His work has appeared in the American Journal of Sociology, the American Sociological Review, the American Journal of Public Health, and Demography.

Time/Place
5/21/2013 from 9:00 AM to 5:00 PM ~ 300 Wallace Hall
5/22/2013 from 9:00 AM to 5:00 PM ~ 300 Wallace Hall
Description
This course offers an applied introduction to the theory and practice of directed acyclic graphs (DAGs) for causal inference. DAGs offer rigorous yet intuitive tools for handling complicated causal problems in the observational social and biomedical sciences. The two primary uses of DAGs are: (1) determining the identifiability of causal effects from observed data, and (2) deriving the testable implications of a causal model. DAGs are also useful for illuminating the causal assumptions implicit in widely used statistical estimation strategies. This course introduces the essential elements for causal reasoning with DAGs and exemplifies these insights with social science examples.
Topics include: non-parametric identification by adjustment; d-separation; the difference between overcontrol bias, confounding bias, and selection bias; what variables to control for and what variables not to control for in observational research; effect heterogeneity; structural assumptions in instrumental variables identification; and recent work on causal mediation analysis.
Please note that this course focuses on spotting and understanding causal opportunities and causal problems. It is not a course on statistical methods (no software component). Students will discuss numerous exercises in class and solve a short homework assignment for the second day.
Prerequisites
The only prerequisite is a basic understanding of multiple regression.
Hardware/Software Requirements
This course will not involve using a computer.
Downloads
None