[Skip to Content]
[Skip to Content Landing]
May 1, 2013

Falsification End Points for Observational Studies—Reply

Author Affiliations

Letters Section Editor: Jody W. Zylke, MD, Senior Editor.

Author Affiliations: Department of Health Care Policy, Harvard Medical School, Boston, Massachusetts (Dr Jena; jena@hcp.med.harvard.edu); and Medical Oncology Branch, National Cancer Institute, Bethesda, Maryland (Dr Prasad).

JAMA. 2013;309(17):1769-1771. doi:10.1001/jama.2013.3112

In Reply:Falsification hypotheses can help adjudicate whether observational associations are robust or whether they reflect selection bias among patients who receive an intervention. Dr Groenwold thoughtfully expands on a prerequisite to proper falsification analyses: the falsification hypothesis must test a putative mechanism of bias.

Consider, for example, the question posed by Groenwold of whether β-blocker therapy reduces perioperative cardiac risk. Even after adjusting for observed patient demographics and claims-based clinical characteristics, an estimated association between β-blocker therapy and cardiac risk may still be confounded by unobserved patient and physician characteristics, including unmeasured socioeconomic characteristics.