[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]
Views 659
Citations 0
February 27, 2013

Emergence of Large Treatment Effects From Small Trials—Reply

Author Affiliations

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

Author Affiliations: Stanford Prevention Research Center, Stanford University School of Medicine, Stanford, California (Dr Ioannidis; jioannid@stanford.edu); Institute of Education and Sciences, German Hospital Oswaldo Cruz, São Paulo, Brazil (Dr Pereira); and GlaxoSmithKline, King of Prussia, Pennsylvania (Dr Horwitz).

JAMA. 2013;309(8):768-769. doi:10.1001/jama.2012.208831

In Reply: We agree with Drs Batterham and Hopkins that small studies are not necessarily inherently flawed. However, probabilistically speaking, even in the absence of biases, small-sized trials are more prone to provide overestimates (or underestimates) compared with larger trials.

Thus, evidence from scattered small studies is easier to distort than evidence from large trials because analyses with the most impressive results are more likely to be published compared with studies showing underestimated treatment effects.

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