Doubly robust identification for causal panel data models
Abstract
We study identification and estimation of causal effects in settings with panel data. Traditionally, researchers follow model-based identification strategies relying on assumptions governing the relation between the potential outcomes and the observed and unobserved confounders. We focus on a different, complementary approach to identification, where assumptions are made about the connection between the treatment assignment and the unobserved confounders. Such strategies are common in cross-section settings, but rarely used with panel data. We introduce different sets of assumptions that follow the two paths to identification and develop a double robust approach. We propose estimation methods that build on these identification strategies.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jun 24, 2022
- Source ID
- 10.1093/ectj/utac019
Entities
People
- Dmitry Arkhangelsky
- Guido Imbens
Organizations
- CEMFI
- Office of Naval Research
- Stanford University