[Skip to Content]
Access to paid content on this site is currently suspended due to excessive activity being detected from your IP address Please contact the publisher to request reinstatement.
[Skip to Content Landing]
October 2010October 18, 2010

Comparing Treatments Using Observational Study DesignsWhat Can We Do About Selection Bias?

Author Affiliations

Author Affiliations: Departments of Surgery, University of Michigan, Ann Arbor (Dr Dimick) and University of Texas Southwestern School of Medicine, Dallas (Dr Livingston).

Arch Surg. 2010;145(10):927. doi:10.1001/archsurg.2010.223

In this issue of Archives, Johnson et al1 report findings from a single-center observational study evaluating the relationship between early transfusion of fresh frozen plasma (FFP) and multiple organ failure. Although the authors appropriately label their findings' association in the title and prose, their recommendations clearly imply causation. Specifically, they call for a reexamination of policies aimed at early FFP transfusion. However, there is a key methodologic flaw in that this reexamination threatens the validity of this study and limits the conclusions we can draw from it.

First Page Preview View Large
First page PDF preview
First page PDF preview