Hi Agus ( list).
Thanks for sending along your files. This is what I discovered:
1) Your tree had an extra taxon (robusta) not represented in your data.
2) However, when removed the analysis still doesn't work because some of
your environmental variables seem to be perfect linear combinations
Hi Agus.
To follow up on (3), I just posted a version of new version of the
function that strips the imaginary part of the canonical correlations if
it is zero. (Details here:
http://blog.phytools.org/2013/07/complex-numbers-in-r-and-new-version-of.html).
All the best, Liam
Liam J. Revell,
Dear list
Im trying to use the function fitContinuous implemented in Geiger (Harmon
et al., 2008) to adjust the different macroevolutionay models to my data
set. However, when run the models trend and OU the resuls show the
following error: Parameter estimates appear at bounds (beta to trend