Dear helpers: I am recently doing some research on enquity returns and I have 2 heavy-tailed distribution and the qqnorm is attached. My aim is to cluster the data into 3 clusters: lower-part tail, body and higher-part tail. I am wondering what is good approach or reference to this question. I believe there must be a lot of research already in this field but I just don't know how to find them by googling, for example. I posted the question to r-help already but I did not get a satisfactory answer yet. Thanks,
Weiwei Shi, Ph.D "Did you always know?" "No, I did not. But I believed..." ---Matrix III -------------- next part -------------- A non-text attachment was scrubbed... Name: qq1.zip Type: application/zip Size: 17221 bytes Desc: not available Url : https://stat.ethz.ch/pipermail/r-sig-finance/attachments/20050504/5bd7b5c3/qq1.zip