MacQueen, Don <macqueen1 <at> llnl.gov> writes:
>
> It's a pretty simple formula, according to the sources I found.
>
> Here's a function that looks right to me, but I have no independent
> calculation with which to check it.
> (no guarantees!)
>
> Hb <- function(ns) {
> N <- sum(ns)
> (lfactorial(N) - sum(lfactorial(ns)))/N
> }
>
> > ns <- c(3,5,2,8)
> > Hb(ns)
> [1] 1.028802
Another source I found said that the index should be scaled
by its maximum value, which assumes that all species are of
equal diversity, which would be
(lfactorial(N)-sum(lfactorial(mean(ns)))/N
(the fact that mean(ns) is non-integer is not a problem; lfactorial()
accepts non-integral values).
Future questions like this *might* get more traction on
the r-sig-ecol...@r-project.org list ...
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
