Hello! I'm looking for articles that discuss the fact that sample size should be substantially greater than the number of variables included in the analysis (= total number of landmark coordinates). So that for 2D [or 3D] data the number of specimens should be at least greater than twice [or three times] the number of landmarks. Which are the limits of this rule? and what are the possible consequences of not following it? If somebody has articles that discuss all this I would be very grateful!! Thanks a lot, Fernando Ventrice
-- Replies will be sent to the list. For more information visit http://www.morphometrics.org
