COMMON MISTEAKS
MISTAKES IN
USING STATISTICS: Spotting and Avoiding Them
Suggestions for Reviewers, Referees, Editors (and
Members
of Institutional Review Boards)
- Base acceptance on on the quality of
the design,
implementation, analysis, and writing (as well as the importance of the
questions being studied), but not
on the results of the analysis
- See Suggestions
for Researchers.
- Have authors followed these guidelines?
- See Suggestions for
Reading
Research.
- Is the paper written to facilitate
reading following
these suggestions?
- How would a
reader following these guidelines rate the research?
- Is the research "reproducible"? That is, is
the
information given in the paper and the material referenced in the paper
adequate for someone to duplicate the data gathering and analysis?
- Check to be sure power
calculations are prospective, not retrospective.
- As needed, join with others to help promote
"best
practices" in research and publication.
- Consult the references below for more
suggestions.
Further References:
J. Coyne (2009), Are most positive findings in health
psychology false ... or at least somewhat exaggerated?, European Health
Psychologist, Vol. 11, No. 3, pp. 49 - 51.
J. P. A. Ioannidis (2008) Why most discovered true associations are
inflated, Epidemiology vol 19
(5), 640 - 648.
C. Kilkenny et al, Improving
Bioscience Research Reporting: The ARRIVE Guidelines for Reporting
Animal Research, PLoS Biol
8(6): e1000412.
doi:10.1371/journal.pbio.1000412
Nature.com
Peer-to-Peer blog Blog for peer reviewers and about peer review
PLoS
Medicine Editors (2005) Minimizing Mistakes and Embracing Uncertainty,
PLoS Med 2(8): e272, doi:10.1371/journal.pmed.0020272. This is an
editorial response to the Ioannis article mentioned in the Introduction to this website.