[R] Quelplot

[Michael Friendly]

On 9/21/2011 3:11 PM, Hadley Wickham wrote:
> Hi all,
>
> Does anyone have an R implementation of the queplot (K. M. Goldberg
> and B. Iglewicz. Bivariate extensions of the boxplot. Technometrics,
> 34(3):pp. 307–320, 1992)?  I'm struggling with the estimation of the
> asymmetry parameters.

Do you have some code you have tried or don't you know how to calculate 
P_1 and P_2?  The description is not particularly explicit, but the
major/minor axes of the ellipse are defined in terms of standard scores
for X and Y as
Z1 = Y + X
Z2 = Y - X

If you can figure out what they mean by "proportion of the total 
standard deviation due to residuals...", then something like

P_1 = sum(Z_1>0) / n
P_2 = sum(Z_2>0) / n

Maybe Boris can help.

Thanks for bringing this to our attention.  If the bagplot is a totally
non-parametric analog of a bivariate boxplot, the quelplot might
be a 2df parametric version.

-Michael



-- 
Michael Friendly     Email: friendly AT yorku DOT ca
Professor, Psychology Dept.
York University      Voice: 416 736-5115 x66249 Fax: 416 736-5814
4700 Keele Street    Web:   http://www.datavis.ca
Toronto, ONT  M3J 1P3 CANADA