3
$\begingroup$

enter image description here I have dones a PCA analysis about measurement of a fish morphometric between female and male. After the PCA result came out with biplot graph, I was a little bit confused to interpret this data. It seems all the vector didn't representing the data because the data dispersed in the opposite axes. Could you help me to analyze this?

Note:

  • blue=male
  • pink=female
  • POL=post orbital length
  • mow=mouth opening width
  • cpl=caudal peduncle length
  • podl=post dorsal length.
$\endgroup$
  • $\begingroup$ Please make a search biplot pca on the site $\endgroup$ – ttnphns Jul 19 '18 at 13:15
0
$\begingroup$

First of all, the vectors represent the variables (with direction and magnitude as any vector would) and the points represent your observations.

It means that only 2 variables contribute to the second PC (POL and MOW) and that they are almost orthogonal (uncorrelated) to all the other variables. And all the the other variables are mostly associated with the first PC (i.e, they are correlated).

It would also seem that you cannot dissociate the male and female categories in your that PC space.

I don't know about the scale of the variables but it's a good idea to whiten your data and then perform PCA again.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.