This course covers empirical identification strategies for using non-experimental data to conduct causal analysis. Students will become familiar with common methodological problems that prevent causal interpretation, and strategies to address it. Students will learn how to and when to implement commonly used econometrics tools such as differences-in-differences, instrumental variables, and regression discontinuity designs. Students will replicate past studies in healthcare that have employed these models and will become familiar with data graphing techniques often used to argue for causal interpretation. Additionally, students will produce three short papers using each of the three strategies. Students are strongly encouraged to connect these brief reports with their thesis.