> > > Some authors such as Pielou make the distinction between interpreting the >data at hand using cluster analysis and ordination, and using multivariate >statistics based on inference,
Indeed, the distinction must always be kept between pattern recognition approaches (e.g., PCA) and inferential (probability based, null hypothesis testing) statistics. Random sampling is much less important to the former. Robert S. Corruccini Professor and Distinguished Scholar Anthropology Dept. Southern Illinois University Carbondale, Il 62901-4502
