Hi Olivier,
You can call scagnostics either with two vectors, or a data.frame (in
which case it computes all pairwise scagnostics).
I just double checked to make sure I didn't accidentally misname the
vector of scagnostics in R, and it doesn't look like I did, so could
you please send me a reproducible example so I can look into it more
closely.
Thanks,
Hadly
On 7/9/07, Olivier ETERRADOSSI <olivier.eterradossi at ema.fr>
wrote:> Hi Hadley,
> thank you for providing this "scagnostics" primer....
> I was trying to do some basic testing, and I see that I probably missed
> some points :
> first it's not clear for me if the argument of "scagnostics"
should be
> raw data or "processed" data (results of calling
"splom" or whatever...).
> If the first, I thought (from Wilkinson & al.) that if taking as an
> example variables x and y being the coordinates of a circle, I should
> find in scagnostics(x,y)$s :
> Skinny = 0 and Convex =1.
> I get Skinny = 1 and Convex =0.... What am I missing ?
> (My God, I'm feeling myself going to be "Ripleyed" !.....)
> Regards, Olivier
>
> --
> Olivier ETERRADOSSI
> Ma?tre-Assistant
> CMGD / Equipe "Propri?t?s Psycho-Sensorielles des Mat?riaux"
> Ecole des Mines d'Al?s
> H?lioparc, 2 av. P. Angot, F-64053 PAU CEDEX 9
> tel std: +33 (0)5.59.30.54.25
> tel direct: +33 (0)5.59.30.90.35
> fax: +33 (0)5.59.30.63.68
> http://www.ema.fr
>
>