| pco {labdsv} | R Documentation |
Principal Coordinates Analysis
Description
Principal coordinates analysis is an eigenanalysis of distance or metric dissimilarity matrices.
Usage
pco(dis, k=2)
Arguments
dis |
the distance or dissimilarity matrix object of
class "dist" returned from
|
k |
the number of dimensions to return |
Details
pco is simply a wrapper for the cmdscale function
of Venebles and Ripley to make plotting of the function similar to
other LabDSV functions
Value
An object of class ‘pco’ with components:
points |
the coordinates of samples on eigenvectors |
Note
Principal Coordinates Analysis was pioneered by Gower (1966) as an alternative to PCA better suited to ecological datasets.
Author(s)
of the ‘cmdscale’ function: Venebles and Ripley
of the wrapper function David W. Roberts droberts@montana.edu
References
Gower, J.C. (1966) Some distance properties of latent root and vector methods used in multivariate analysis. Biometrika 53:325-328.
See Also
Examples
data(bryceveg) # returns a vegetation data.frame
dis.bc <- dsvdis(bryceveg,'bray/curtis')
# returns an object of class dist'
veg.pco <- pco(dis.bc,k=4) # returns first 4 dimensions
plot(veg.pco)