[R] cauculating dissimilarities in R

virgin virgin at seychelles.sc
Tue Sep 26 07:40:42 CEST 2006


Dear All,
I’ve got a statistical question on calculating
dissimilarities in R.
I want to calculate the different types of dissimilarities
on the ‘flower’ dataset found in the package
‘cluster’. Flower is a data frame with 18 observations
on 8 variables. Variable 1 and 2 are binary, variable 3 is
asymmetric binary, variable 4 is nominal, variable 5 and 6
are ordered and variable 7 and 8 are interval scaled.

Commands to load the dataset in R.
library(cluster)
data(flower)
flower


What are the different types of dissimilarities that can be
calculated on such a dataset?  
Do I need to group the types of variables first i.e. all
binary together then run the calculation?  Do I use
dissimilarity indices such as Jaccard or should it be
classification function such as ‘daisy’ which should be
used? 

Many thanks,

Elvina Payet (MSc)
University of La Reunion



More information about the R-help mailing list