K means cluster analysis is sometimes run on orthogonal principle component scores instead of individual attributes (such as in marketing research when dealing with a lengthy attitudinal battery). Many analysts don't recommend this practice for various reasons (e.g., factor analysis factors might mask key discriminating attributes, the non-correlation between factors artificially spreads people out in space, etc.).
If using latent class cluster analysis to find groups using attitudinal battery items as inputs, do the same criticisms apply for using orthogonal principle component scores as analysis basis variables OR is it a more justifiable practice for latent class cluster analysis versus K means cluster analysis? Iím looking for a point of view/recommendation on using orthogonal principle component scores versus individual attitudinal attributes as inputs for latent class cluster analysis. To what extent are issues such as collinearity between attributes, lack of correlation between orthogonal principle component scores, etc. damaging (or non damaging) for latent class cluster analysis?
I think orthogonal components are problematic for both K-means clustering and latent class clustering. If one wants to reduce the dimensionality before clustering it would seem that it would be better to use estimated factor scores from an oblique factor analysis solution. Using the item-level information might be preferable but could lead to a multitude of clusters.