Reporting Bias

From Clinfowiki
Revision as of 00:59, 29 April 2015 by Jaucoin (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Only a fraction of the research that is done ends up being reported in the published literature. Reporting bias occurs when features of the results (such as statistical significance) influence how widely, or even whether, they are circulated.


Types of Reporting Biases:

  • Time lag bias: rapid vs delayed publication based on the results
  • Language bias: publication in a particular language based on the results
  • Multiple publication bias: single vs multiple publications based on the results
  • Location bias: publication in a journal with a different ease of access based on the results
  • Citation bias: citation vs non-citation of findings based on the results
  • Outcome reporting bias: selective reporting of some outcomes based on the results


Results that are positive and statistically significant have been found to be more likely to:

  • Be published
  • Be published rapidly
  • Be published in English
  • Be published as part of more than one article
  • Be published in high-impact journals
  • Be cited by others

References:

Sterne JAC, Egger M, Moher D (editors). Chapter 10: Addressing reporting biases. In: Higgins JPT, Green S (editors). Cochrane Handbook for Systematic Reviews of Intervention. Version 5.1.0 (updated March 2011). The Cochrane Collaboration, 2011. Available from www.cochrane-handbook.org. [1]

Submitted by Jennifer Aucoin