User Tools

Site Tools


en:tbpca_examples

Unconstrained ordination

Transformation-based principal component analysis (tb-PCA)

Example 1: PCA on species data transformed using Hellinger transformation

In this example we will use vegetation data from Vltava river valley dataset, and we will analyse them by PCA after pre-transformation by Hellinger transformation.

vltava.spe <- read.delim ('https://raw.githubusercontent.com/zdealveindy/anadat-r/master/data/vltava-spe.txt', row.names = 1)
vltava.spe.hel <- decostand (log1p (vltava.spe), 'hellinger') # the species data (percentage scale) are first log transformed, and then transformed using Hellinger transformation
 
PCA <- rda (vltava.spe.hel)
 
source ('http://www.davidzeleny.net/anadat-r/doku.php/en:numecolr:cleanplot.pca?do=export_code&codeblock=0') # define the cleanplot.pca function
cleanplot.pca (PCA)

These ordination diagrams do not look too helpful (you need to click to enlarge them to see more details) - but we will see later how to visualize the results of ordination more effectively.

en/tbpca_examples.txt · Last modified: 2018/03/30 23:04 (external edit)