P.Mean: Can I please skip the Bonferroni adjustment? (created 2008-08-19).
This page is moving to a new website. I ran multiple correlation analysis for abundances, richness (species
density), and diversity of different growth forms in four different landscapes
in Colombian Amazonia. My questions is: Do I have to calculate a Bonferroni
test to adjust for each probability? I always get nervous about these questions where people seem to be wanting
my permission to do something that they know is bad. Conducting multiple
hypothesis tests without any adjustment to the alpha level is certainly
considered bad by some. But you are actually off the hook, because there is no
consensus in the research community about when to apply the Bonferroni
correction. Certain disciplines use Bonferroni extensively and other use it
rarely. I suspect you don't want to use a Bonferroni adjustment because you lose
some of your statistically significant results when this happens. So don't use
it. There are only two times when a Bonferroni adjustment is mandated. First,
you must use a Bonferroni adjustment if you promised that you would in the
original research protocol. Second, you must use the Bonferroni adjustment if
someone in a position of authority over you demands it. This person could be
your boss or someone who exercises control over whether you can publish your
results (that is, a referee or a journal editor). By the way, my opinion (don't use Bonferroni here) is not important, as I
am not in a position of authority over you. When my grand plan to take over
the world is realized, that will change, of course. I would suggest that you re-run the analysis using a Bonferroni adjustment,
but do not report it in your publication. Keep it available if a referee asks
about this. In fact, it will impress the referee if you mention in your
response that you had already run the analysis using Bonferroni. If the
referee does not ask about Bonferroni, then all that you have lost is a little
bit of time. Of course, whether or not you use the Bonferroni adjustment, you should
mention the large number of comparisons as a (minor) limitation in your
discussion section.
This work is licensed under a
Creative
Commons Attribution 3.0 United States License. This page was written by
Steve Simon and was last modified on
2010-04-01. Need more
information? I have a page with general help
resources. You can also browse for pages similar to this one at
Category: Multiple comparisons.