Statistical FAQs
How does JMP pick the initial cluster seeds in K-Means Clustering?
JMP is using the same seed selection that FASTCLUS does, with METHOD=FULL on the intial seeding. Generally, this method starts at observation one and from that picks observations within the dataset that are far apart. Please see the first four paragraphs on the top of page 825 in the SAS/STAT Users Guide, Vol. 1, v6 for a detailed explanation.
FAQ # 2084
Last Updated: 2004 Jun 25
Browse JMP FAQs
Support Documents
Contact JMP Support
919.677.8008 (US)
