Impact evaluation of multiple overlapping programs under a conditional independence assumption |
| |
| Authors: | Nguyen Viet Cuong |
| |
| Institution: | 1. Departments of Critical Care and Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA;2. The Clinical Research, Investigation, and Systems Modeling of Acute Illness (CRISMA) Center, Department of Critical Care, Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA;3. Division of Pulmonary and Critical Care Medicine, University of Michigan, Ann Arbor, MI, USA;4. Robert Wood Johnson Clinical Scholar Program, University of Michigan, Ann Arbor, MI, USA;5. Center for Healthcare Outcomes and Policy, University of Michigan, Ann Arbor, MI, USA;6. Department of Biostatistics, University of Washington, Seattle, WA, USA;7. Department of Emergency Medicine, University of Pittsburgh, Pittsburgh, PA, USA;8. King County Medic One, Division of General Internal Medicine, University of Washington, Seattle, WA, USA;9. Departments of Critical Care, Medicine, Health Policy and Management, University of Pittsburgh Graduate School of Public Health, Pittsburgh, PA, USA;10. Biostatistics and Biomathematics Program, Public Health Sciences Division, Fred Hutchinson Cancer Research Center, Seattle, WA, USA |
| |
| Abstract: | Under the assumption on conditional independence between potential outcomes and program assignment, program impacts measured by the Average Treatment Effect (ATE) and the Average Treatment Effect on Treated (ATT) can be identified and estimated using cross-section regression or propensity score matching (PSM). Traditional impact literature often deals with the impact evaluation of a single program. In reality, one can participate in several programs simultaneously and the programs may be correlated. This paper discusses cross-section regression and PSM methods in this general context. It is shown that under the PSM method, impact of a program of interest can be measured as a weighted average of program impacts on groups with different program statuses. Estimation of impacts of multiple overlapping programs is illustrated using Monte Carlo simulation and an empirical example of impact measurement of international and internal remittances in Vietnam. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
