Whether to use Covariance or Correlation Matrix for PCA

r
correlation
dimensionreduction

#1

In the above image the upper image is of the correlation matrix and the below one is of the covariance matrix.
I am not sure what to use for PCA(cor or cov) as I do not know when we should use which one.Can somebody please help me regarding this.


#2

@pagal_guy,

You should use the covariance matrix when the variable scales are similar and the correlation matrix when variables are on different scales. Correlation matrix standardises the data and it is one of the requirement of using PCA. Both give different results when the scales are different.

Regards,
Mark