Chapter 11 Panel data
While preparing this chapter I learned about the PanelMatch
package (published in February 2020) and corresponding functions. The corresponding parts in the script are tentative at best. I would recommend anyone interested in estimating causal effects with panel data to dive into this new package and the corresponding paper (Imai, Kim, and Wang 2018). In my view the contained functionalities represent the ultimate strategy to estimate causal effects with panel data, namely through finding/comparing treatment and control units that match in terms of their pre-treatment history (regarding treatment, outcome and covariates).
References
Imai, Kosuke, In Song Kim, and Erik Wang. 2018. “Matching Methods for Causal Inference with Time-Series Cross-Section Data.” Princeton University 1.