I'm not sure I understand exactly what you want to do....if you have just one contingency table, and the categories are nominal, then I don't think you have enough data to do any kind of cluster analysis......If both of the variables are ordinal, or, better yet, interval, then you might be able to do something. (but if your data are interval, why a crosstab?). If you have more than one crosstab then you might also be able to do something, e.g. if you have 5 yes-no variables, then people can fall into 32 categories and some might be more likely.
Even at this, I don't think cluster analysis is the best way... Perhaps if you supply some more context about how many variables you have, what they are, and what you would like to be able to conclude, I or someone else here would be able to provide more help Peter Peter L. Flom, PhD Assistant Director, Statistics and Data Analysis Core Center for Drug Use and HIV Research National Development and Research Institutes 71 W. 23rd St www.peterflom.com New York, NY 10010 (212) 845-4485 (voice) (917) 438-0894 (fax) >>> [EMAIL PROTECTED] 3/14/2004 11:16:52 AM >>> I'm trying to do a cluster analysis with a data set that is in the form of a contingency table (i.e. cross tabulation of counts in various categories). I wanted to use k-means but I'm not sure that this is a valid thing to do. Has anyone got any opinions as to whether I should use just hierarchical or k-means. Thanks Keith . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . ================================================================= . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
