I have a score matrix (from PCA) which contains 7 scores for 15,229 observations. I want to automatically sort the observations into groups (clusters) with similar scores. I have a 750 MHz PC with 2GB of RAM at my disposal. Does anyone have any suggestions for dealing with such a large number of observations? Commercial software solutions would be preferable, but any ideas on the general question of grouping large numbers of observations are welcomed as well. Thanks, Mark Mark Nicholas Analytical Research AstraZeneca R&D Mölndal S-431 83 Mölndal, Sweden tel: +46 31 776 1937 fax: +46 31 776 3834