[R] daisy() for gower distance calculation

[Tyler Smith]

On Mon, Nov 20, 2006 at 04:38:13PM +0000, Gavin Simpson wrote:
> If in R, daisy() implements most closely Gower's (1971) similarity
> (expressed as a distance) why shouldn't you use it? 

That's what I didn't get. All I know about daisy is what's on the help
page, and it wasn't clear to me how it related to the Gower
similarity. I had assumed that it was similar (and probably better),
but I did not realise that it provided numerically identical answers
(or at least it could if you wanted it to). After your email I looked
a little deeper, and yes indeed it does produce an identical distance
matrix to the one I get using vegdist (+/- 1.110223e-16).

This being the case there is no reason not to use it, and I expect I
will in future. For the time being, the scripts for my current
analysis use vegdist, which is also fine for my data.

Thanks, this has been very helpful for me!

Tyler