Mini Course in Econometrics
Monday, September 25th and Wednesday, September 27th
1:30 – 3:00 pm, Kellogg Global Hub, room 1410
When Exogeneity Fails: Systematic Methods for Robustness Checks
Description: Many empirical results rely on some kind of exogeneity assumption, like unconfoundedness or random assignment of instruments. Since these assumptions are often not refutable, one may wonder: Just how important are they for our empirical results? The literature on sensitivity analysis provides systematic methods for answering this question. In these two lectures, we’ll survey this literature, beginning with the earliest work on the relationship between smoking and lung cancer to the most recent work using partial identification analysis.
A representative selection of the research we’ll discuss includes:
- Cornfield, Haenszel, Hammond, Lilienfeld, Shimkin, and Wynder (1959) “Smoking and lung cancer: Recent evidence and a discussion of some questions,” Journal of the National Cancer Institute
- Fisher (1966) “On the cost of approximate specification in simultaneous equation estimation,” Econometrica
- Rosenbaum and Rubin (1983) “Assessing sensitivity to an unobserved binary covariate in an observational study with binary outcome,” Journal of the Royal Statistical Society, Series B
- Rosenbaum (1995) Observational Studies, Springer
- Imbens (2003) “Sensitivity to exogeneity assumptions in program evaluation,” American Economic Review P&P
- Altonji, Elder, and Taber (2005) “Selection on observed and unobserved variables: Assessing the effectiveness of Catholic schools,” Journal of Political Economy
- Altonji, Elder, and Taber (2008) “Using selection on observed variables to assess bias from unobservables when evaluating Swan-Ganz catheterization,” American Economic Review P&P
- Conley, Hansen, and Rossi (2012) “Plausibly exogenous”, Review of Economics and Statistics
- Oster (2016) “Unobservable selection and coefficient stability: Theory and evidence,” Journal of Business & Economic Statistics (Forthcoming)