[R] Multivariate kernel density estimation

[Jeroen Ooms]

I would like to estimate a 95% highest density area for a multivariate
parameter space (In the context of anova). Unfortunately I have only
experience with univariate kernel density estimation, which is remarkebly
easier :)

Using Gibbs, i have sampled from a posterior distirbution of an Anova model
with k means (mu) and 1 common residual variance (s2). The means are
independent of eachother, but conditional on the residual variance. So now I
have a data frame of say 10.000 iterations, and k+1 parameters.

I am especially interested in the posterior distribution of the mu
parameters, because I want to test the support for an inequalty constrained
model (e.g. mu1 > mu2 > mu3). I wish to derive the multivariate 95% highest
density parameter space for the mu parameters. For example, if I had a
posterior distirbution with 2 means, this should somehow result in the
circle or elipse that contains the 95% highest density area. 

Is something like this possible in R? All tips are welcome.
-- 
View this message in context: http://www.nabble.com/Multivariate-kernel-density-estimation-tp20894766p20894766.html
Sent from the R help mailing list archive at Nabble.com.