Well: I programmed an script in R using caret package and the results are very interesting ... I have two datasets the first dataset have a linear distribution experimentaly: values are: 4.3 , 5.3, 6.3.. 10.3... the svmRadial kernel work perfectly and I can obtain an R2 = 0.98 between the predicted value and the estimated value. But the second dataset do'nt have a linear distribution of the data experimentaly ...then I can only say that molecules are in the the well, 1, 2, 3, ... 10. When I tested the svmRadial the results are disastrous.... Is related the problem with non-linear regression? Is related the problem with the fact that svmRadial in caret select the RMSD to choice the better model? Thanks in advance Yasset
-- View this message in context: http://r.789695.n4.nabble.com/Bigining-with-a-Program-of-SVR-tp3484476p3580705.html Sent from the R help mailing list archive at Nabble.com. ______________________________________________ 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.
