Testing for bimodality (May 3, 2005).

I have talked about this topic before and it is a rather tricky thing. A recent discussion of tests of bimodality on edstat-l, though, yielded a few promising leads relating to the Dip test of

•  Hartigan JA & Hartigan PM. "The Dip Test of Unimodality", The Annals of Statistics, v13(1):70-84, 1985.

Some links to software to run the Dip test are shown below.

• www.maths.lth.se/help/R/.R/library/diptest/html/dip.html
• cran.r-project.org/doc/packages/diptest.pdf
• lib.stat.cmu.edu/apstat/217

and there is a pdf version of another paper that discusses the Dip test:

• www.economics.ucr.edu/people/russell/02-15.pdf

This webpage was written by Steve Simon and was last modified on 07/08/2008. Category: Statistical theory