Hello,
I am an intern and I am using BRTs to model functional diversity of reef
fish.
I am testing several values of lr and tc together so I can find optimal
settings for y models.
for some of my data, I get the folowwing error message :
"restart model with a smaller learning rate or smaller step size..."
When I reduce lr or n.trees (with very small values), I still get the same
error message.
This is related to the following line in the brt.functions script:
(cv.loss.values[j] > cv.loss.values[j-1]))
the data drames I am working on contain around 60 to 120 lines and I have 51
predictors.
I am new with BRTs and I have no idea how to resolve this issue.
Any help would be appreciated!!
Thanks
Stephanie
*---------------------------
Stéphanie D'agata*
ECOSYM - UMR 5119 cc 93 Bat 24 - Université Montpellier II - Montpellier
COREUS - UR 227 - IRD Nouméa - Nouvelle-Calédonie
**
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
