[R] test for bimodality

[David White]

Dear R users,

I'm looking for a test of bimodality in order to make some decisions about how to procede with an analysis algorithm. I have not come across any such tests in my readings and discussions apart from the Rao which appears to be applicable to cyclic data.

The data I'm interested in characterizing as uni- or bimodal  are frequency x amplitude spectra of consonant speech sounds, where the spectrum, a line graph is treated as a frequency distribution. 

Thanks in advance for your input.

David
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://stat.ethz.ch/pipermail/r-help/attachments/20010513/4c550f2c/attachment.html