I second Diana's commendation of L-moments; in the present context, I seem to remember that the fifth L-moment is suggested as a measure of multi-modality (I don't have Hosking and Wallis to hand to check).
Julian
> -----Original Message-----
> From: A UK-based worldwide e-mail broadcast system mailing list
> [mailto:[log in to unmask]] On Behalf Of Kornbrot, Diana
> Sent: 25 November 2010 10:03
> To: [log in to unmask]
> Subject: Re: [allstat] Characteizing the shape of histograms
> statistically...
>
> Linear moments are amore relaible wy of characterising distribution shape
> than conventionla moments, and are far more accurately estimated, i.w.
> Have smaller standard errors
> http://en.wikipedia.org/wiki/L-moment
> Hosking, J. R. M., & Wallis, J. R. (1997). Regional frequency analysis.
> An approach based on L-Moments. Cambridge, UK: Cambridge University Press.
> Hosking, J. R. M. (1990). L-moments: analysis and estimation of
> distributions using linear combinations of order statistics. Journal of
> the Royal Statistical Society, B, 52, 105-124.
> + if you are interested in climate change hosking's book is salutary
> =sheds light no heat on such debates
> Best
> Diana
>
>
This email has been scanned for all viruses by the MessageLabs Email
Security System.
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|