empirical-methods

Homepage for 17-803 "Empirical Methods" at Carnegie Mellon University

Project maintained by bvasiles Hosted on GitHub Pages — Theme by mattgraham

L21: Hands-on: Interrupted Time Series Analysis With Control (notebook, video)

Lecture21-Interrupted-Time-Series-With-Control

In this lecture we discussed an exciting Nobel prize idea – natural experiments.

We spent most of the lecture on a hands-on activity, showing students how to model jointly two interrupted time series, one for treated and one for controls, effectively recreating a difference-in-differences design. I used an artificial dataset for this. You can find an example solution in the ITS notebook from last time.

In the second part of the lecture we went over the synthetic control method, in particular the California Prop 99 case study. See the Abadie et al and Arkhangelsky et al papers. We went over this notebook illustrating the method.

Unfortunately I lost most of the video recording.

Lecture Readings

Bottomley, C., Scott, J. A. G., & Isham, V. (2019). Analysing interrupted time series with a control. Epidemiologic Methods, 8(1), 20180010.

Fichtenberg, C. M., & Glantz, S. A. (2000). Association of the California Tobacco Control Program with declines in cigarette consumption and mortality from heart disease. New England Journal of Medicine, 343(24), 1772-1777.

Arkhangelsky, D., Athey, S., Hirshberg, D. A., Imbens, G. W., & Wager, S. (2021). Synthetic difference-in-differences. American Economic Review, 111(12), 4088-4118.

Abadie, A., Diamond, A., & Hainmueller, J. (2010). Synthetic control methods for comparative case studies: Estimating the effect of California’s tobacco control program. Journal of the American statistical Association, 105(490), 493-505.