I have a data of 300 participants who all filled in a questionnaire. I want to cluster these people regarding different features (burnout, engagement etc.).
Some of the measurements are on a likert scale 1-4, some 1-5 and some 1-6. Should I standardize them so that they all would have a mean of 0 and standard deviation of 1?
I'm thinking about using the K-means or two-step cluster analysis. I've read that this should only be used when the variables are contionuous (not ordinal as in Likert scale), but is it still ok to use the K-means/two-step? Or do you have any other options, I'm using SPSS.