Hi, If you want parametric modes you could fit mixtures with different numbers of components and select the best model with your favourite model-selection criterion. Various packages such as mclust and fitdistr may be helpful in doing this, the cluster task view has many more: http://cran.at.r-project.org/src/contrib/Views/Cluster.html I am not aware of non-parametric mode testing routines in R, which ones were you thinking of? Hth, Ingmar
> From: array chip <[EMAIL PROTECTED]> > Date: Mon, 9 Oct 2006 14:28:32 -0700 (PDT) > To: <r-help@stat.math.ethz.ch> > Subject: [R] bimodal / trimodal > > Hi, is there any package/function that can tell if a > numeric vector (continuous data) has a bimodal or > trimodal distribution and caluclate the location of > the corresponding modes? > > Thanks > > ______________________________________________ > R-help@stat.math.ethz.ch 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. ______________________________________________ R-help@stat.math.ethz.ch 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.
