Posted: April 2, 2020

How Do You Know Which Health Care Effectiveness Research You Can Trust? A Guide to Study Design for the Perplexed


The purpose of this Editor's Choice article is translational in nature. It is intended to illustrate some of the most common examples of potential study bias to help policy makers, journalists, trainees, and the public understand the strengths and weaknesses of various types of health care research and the kinds of study designs that are most trustworthy. It is neither a comprehensive guide nor a standard research methods article. The authors intend to add to these examples of bias in research designs in future brief and easy-to-understand articles designed to show both the scientific community and the broader population why caution is needed in understanding and accepting the results of research that may have profound and long-lasting effects on health policy and clinical practice.


Douglas Starr, MS, Boston University
Stephen B. Soumerai, ScD, Harvard Medical School
Sumit R. Majumdar, MD, University of Alberta

Learner Audience

Undergraduate Medical Education (UME), Graduate Medical Education (GME), Continuing Medical Education/Continuing Professional Development (CME/CPD), Interprofessional


Systems Based Practice

Resource Type(s)

Distance Learning - Synchronous

Instructional Method(s)

Discussion, Small Group [≤12]
Discussion, Large Group (>12)


Population Health, Health Information Technology, Public Health Sciences, Health Policy, Research Design, Health Care Effectivness, Program Evaluation, Translational Education, Health User Bias, Volunteer Selection Bias, Confounding by Indication, Social Desirability Bias, History Bias