[Skip to Navigation]
Sign In
Guide to Statistics and Methods
January 29, 2020

Practical Guide to Health Policy Evaluation Using Observational Data

Author Affiliations
  • 1Department of Surgery, University of Michigan, Ann Arbor
  • 2Center for Healthcare Outcomes and Policy, University of Michigan, Ann Arbor
  • 3Gillings School of Global Public Health, Department of Biostatistics, University of North Carolina at Chapel Hill
JAMA Surg. 2020;155(4):353-354. doi:10.1001/jamasurg.2019.4398

The fundamental goal of policy analysis is to understand the effect of an intervention on patients, health care professionals, or hospitals. Although a randomized controlled design is considered the criterion standard for isolating a causal effect, such a design is rarely plausible in health policy evaluation. As such, researchers often rely on observational data to evaluate a policy’s consequences.1 For example, recent analyses of the association of the Patient Protection and Affordable Care Act (ACA) with outcomes for surgical patients have shown important gains in insurance coverage, timely access to care, and increased rehabilitation facility access after discharge.2-4 While analyses of observational data alone cannot determine causality, valuable evidence regarding their impact can be drawn when applying best analytic practices from across academic disciplines.1

Add or change institution