I have done a multiple correspondence analysis based on 10 factors: every factor is a Yesor Noquestion.

The first factor give 22.3% of the total variance and the second 13.6%. I am used to Principal Component Analysis (PCA) and to having a high percentage (>70%).

Question1: Is a total percentage of 35% (22+13) enough for an MCA?

Question2: base on the image attached, is there any implication when the variables are close to the second axis?

Any other comment about the MCA I have done is appreciated.

enter image description here

  • $\begingroup$ Correspondence analysis is an analysis of contingency table (such as frequency cross-table). What is the dimensionality of your table? Can you show us your table? $\endgroup$ – ttnphns Jun 6 '14 at 13:25
  • $\begingroup$ 10 variables and every variable have two levels. (20,20) $\endgroup$ – user42987 Jun 6 '14 at 14:53
  • $\begingroup$ Sorry I still don't understand your frequency cross-tabulation. I even suspect that you may be doing something wrong. Show the table please. $\endgroup$ – ttnphns Jun 6 '14 at 15:04

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.