Hi,
MM recommended to send this to R-devel:
As far as I know, the only method to compute Kendall's tau is to perform
cor.test with method="kendall". I suggest that
1) this should be easier to find, namely with help.search("kendall")
and/or link from cor,
2) cor should be given a method parameter like cor.test so that
Kendall and Spearman correlations can be computed without doing the test.
Best,
Christian
--
***********************************************************************
Christian Hennig
Seminar fuer Statistik, ETH-Zentrum (LEO), CH-8092 Zuerich (currently)
and Fachbereich Mathematik-SPST/ZMS, Universitaet Hamburg
hennig@stat.math.ethz.ch, http://stat.ethz.ch/~hennig/
hennig@math.uni-hamburg.de, http://www.math.uni-hamburg.de/home/hennig/
#######################################################################
ich empfehle www.boag.de