I have a set of continuous distributions representing the leaf area density found at different heights through a forest canopy. e.g. like that found in Whitehurst et al. (2013):

For each of these foliage density profiles I also have information on the tree species diversity and tree trunk diameter of each tree contributing to the leaf area found in these profiles.

What statistical techniques can I use to test whether these foliage density profiles vary meaningfully as a result of various metrics related to tree diversity such as number of tree species, variance of trunk diameter?

  • $\begingroup$ One useful thing to do is to visually inspect a 3D scatterplot of the data from different viewing angles and see if any pattern seems obvious. Do you have access to software capable of 3D scatterplotting and 3D surface (z=f(x,y) modeling? $\endgroup$ – James Phillips Jan 10 at 17:29

You are looking for functional data analysis, which is the branch of statistics where "observations" are entire curves, which are then modeled in various ways. There are a couple of eponymous textbooks cited in Wikipedia. We also have a tag .


Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Not the answer you're looking for? Browse other questions tagged or ask your own question.