2

Factoextra is an excellent package to visualize the PCA result. And what I want to know is the value of the reference line in the PCA contributions plot. In this case it is about 10%. Is there a general principle what is this value?

library(factoextra)
library(FactoMineR)
df <- decathlon2[1:23, 1:10]
res.pca <- PCA(df,  graph = FALSE)
fviz_contrib(res.pca, choice = "var", axes = 1, top = 10)

An example :

StupidWolf
  • 45,075
  • 17
  • 40
  • 72
Minyi Han
  • 807
  • 1
  • 8
  • 15
  • 1
    Read the [documentation](http://www.sthda.com/english/wiki/fviz-contrib-quick-visualization-of-row-column-contributions-r-software-and-data-mining) for `fviz_contrib`: "A reference dashed line is also shown on the barplot. This reference line corresponds to the expected value if the contribution where uniform." – Marius Jul 06 '17 at 00:48
  • @Marius, I have read this documentation, how can I know what the specific value is? – Minyi Han Jul 06 '17 at 01:10
  • thanks, I see, it is 100/length(contrib) – Minyi Han Jul 06 '17 at 01:25
  • Yes, it's just 100 divided by the number of variables, i.e. the average contribution that all values would be equal to if they all had the same contribution. – Marius Jul 06 '17 at 01:41

0 Answers0