Letters Small studies in meta-analyses

Making the best of a little

BMJ 2010; 341 doi: https://doi.org/10.1136/bmj.c4463 (Published 24 August 2010) Cite this as: BMJ 2010;341:c4463
  1. Sebastian Straube, physician-scientist1,
  2. R Andrew Moore, senior research fellow2,
  3. Sheena Derry, senior research officer2,
  4. Phil J Wiffen, director of operations and training3
  1. 1Department of Occupational and Social Medicine, University of Göttingen, Waldweg 37 B, D-37073 Göttingen, Germany
  2. 2Pain Research and Nuffield Department of Anaesthetics, University of Oxford, Churchill Hospital, Oxford OX3 7LJ
  3. 3UK Cochrane Centre, Summertown Pavilion, Oxford OX2 7LG
  1. sebastian.straube{at}googlemail.com

    Nuesch and colleagues confirm that the effects of small studies can distort the results of meta-analyses.1 More important than this potential distortion, however, is the potential for getting completely the wrong answer from a meta-analysis that contains only small trials.

    The problem, of course, is that many, if …

    View Full Text

    Sign in

    Log in through your institution

    Free trial

    Register for a free trial to thebmj.com to receive unlimited access to all content on thebmj.com for 14 days.
    Sign up for a free trial

    Subscribe