This question already has an answer here:

I performed a PCA on some data related to habitat (different types of vegetation cover, soil water etc.), but there were some variables that I did not include in the PCA because they were not strongly correlated with any of the other variables. I selected the first three principal components from the PCA whose eigenvalues were above 1.

Now I want to run a multiple regression to analyse what variables will predict bird density. Is it valid to include my three principal components as well as the variables that I did not include in the PCA into this regression?


marked as duplicate by amoeba says Reinstate Monica, jbowman, Michael Chernick, AdamO, whuber regression Jan 18 '18 at 21:28

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.