Hi,

In the course of cross validation of linear model use the R script below

*lin.kcv <- krige.cv <http://krige.cv>(yield ~ 1, canmod.sp, model =
lin.var,nmax=100, nfold = 5)*

I received a warning message

Warning message:In sqrt(ret[[var.name]]) : NaNs produced


This gives me strange value of RMSE to be 364.9795



But I got reasonable result for other model like

Spherical   0.6618279

Gaussian    0.6216419

Exponential

0.6498786



What does this error message means?



Thank you.

        [[alternative HTML version deleted]]

_______________________________________________
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Reply via email to