A note on the triple difference in economic models

Abstract

This article shows when a triple difference strategy using an imperfect control category improves on the double difference strategy for estimating an average treatment effect. For example, a product is treated in one place and not another leading to a double difference strategy. When does comparison with an untreated product in triple difference strategy improve accuracy?

Keywords:

• Difference in difference
• triple difference
• policy evaluation
• average treatment effect

JEL Classification:

• C21
• C25
• C51

Additional information

Funding

We thank the Giannini Foundation for support.