I have a data set with six continuous variables. I would like to perform a multiple correspondence analysis (MCA) with fuzzy coding. I was able to create the fuzzy coding, so for each original variable I have three “dummy” variables ranging from 0 to 1. Apparently, I am missing a step in performing the MCA, since for each “dummy” variable I get many categories (instead of only three), although in the papers I read the maps/graphs present only a few categories (such as high, medium, low). What am I missing here? I am using both SPSS and Stata.

  • $\begingroup$ I assume "fuzzy" here means that the dummy variables can take values between zero and one, Your software maybe takes that as additional levels, but you need to treat it just as a usual dummy variable. $\endgroup$ – kjetil b halvorsen Apr 8 '17 at 21:07

MCA is used for dealing with categorical data.

Since your dataset contains only 6 continuous data, in other numerical, the factory analysis method that you can use is PCA.

I'm not sure why there's the need to perform the fuzzy coding here.


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.