Sorry for posting so much on this topic! Don't get me wrong, I am very happy with TPS and well aware of its many convenient properties. It's a great, practical tool both for interpolation and statistical analysis.
But I would maintain caution about giving any morphogenetic interpretation to TPS. Biological shape is generally a result of differential growth, not mechanical bending (although mechanics will. also play a role, of course). If one is after a way of decomposing shape change that can be given a more direct morphogenetic interpretation, one should look into, for example, inversion of allometric growth field models (see Hammer in Elewa, 2004: Morphometrics - applications in biology and paleontology, for some vague ideas about this). And again, there are other smoothness criteria than TPS, although I would probably not use them for biological morphometrics. Oyvind Hammer Geological Museum University of Oslo > TO: morphmet readers > FROM: Fred Bookstein > RE: why the thin-plate spline? > > Still, there is a biological interpretation of that global > bending. -- Replies will be sent to the list. For more information visit http://www.morphometrics.org
