I have performed PCA over a data set containing 25 items (variables). PCA was performed in a view to reduce the number of items (variables) from the data set, so as to move forward with analysis. Opting for Varimax rotation. The rotated component matrix is shown below Rotated Component Matrix after PCA. The Communalities is show below Communalities the question is which Items (variables) should i reject from the data set and why based on the output.

  • $\begingroup$ 1) Can you post the cumulative variance explained by the factors? 2) Can you elaborate on the input variables 3) Can you talk about what you want to do with the dimensionally reduced variables? $\endgroup$ – BKay Feb 5 '15 at 1:24
  • 1
    $\begingroup$ I think, and it's possible I'm in the minority here, you should move this to cross validated. PCA is absolutely used in economics, but I think you might get more help there. $\endgroup$ – jayk Feb 6 '15 at 23:02

Your Answer

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

Browse other questions tagged or ask your own question.