AbstractCluster analysis can be used to identify homogenous subgroups in many fields, including psychology and psychiatry. However, most clustering methods implemented in general‐purpose statistical packages are heuristic and can be criticized in principle for their lack of an underlying statistical model. Furthermore correlations between variables are generally ignored by standard methods. The question addressed here is whether currently available commercial software (S‐PLUS), which provides model‐based methods for clustering correlated continuous data, should be used for clustering data derived from questionnaires. Such data may be either continuous or ordinal in nature and typically exhibit correlations. Performance is assessed in this study on simulated data sets containing distinct multivariate normal subpopulations, both before and after mapping the simulated data onto an ordinal scale. A practical example showing how correlated data can be cluster‐analysed using these methods is given. The conclusion is that model‐based methods are certainly worthwhile for continuous data. However, their benefit, in particular their ability to deal with correlated data, is not marked for ordinal data. Simpler methods such as Ward's method may be almost as effective in this situation. Copyright © 2006 John Wiley & Sons, Ltd.