Doubly Robust Identification for Causal Panel Data Models

• Tác giả: Dmitry Arkhangelsky, Guido W Imbens
• Ngôn ngữ: eng
• Ký hiệu phân loại: 003.1 System identification
• Thông tin xuất bản: 2019
• Bộ sưu tập: Metadata
• ID: 163390

Tóm tắt

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 doubly robust approach. We propose estimation methods that build on these identification strategies.