Program Impact Evaluation Using a Matching Method with Panel Data

Nguyen Viet Cuong

Statistics in Medicine, Volume 31, Issue 6, pp. 577-88


Difference-in-differences with matching is a popular method to measure the impact of an intervention in health and social sciences. This method requires baseline data, that is, data before interventions, which are not always available in reality. Instead, panel data with two time periods are often collected after interventions begin. In this paper, a simple matching method is proposed to measure the impact of an intervention using two-period panel data after the intervention. The method is illustrated by the measurement of the effect of health insurance in Vietnam using household panel data.

Full text for Wiley Online Library subscribers only.

© 2016 Mekong Development Research Institute

Address: Floor 8, Machinco Building, 444 Hoang Hoa Tham, Hanoi, Viet Nam.
Telephone: +84 024 3247 4668       Fax: +84 024 3247 4596