AnsweredAssumed Answered

Emprical Bayesian Kriging

Question asked by harpssi on Jun 25, 2014
Latest reply on Jun 27, 2014 by mboeringa2010
I'm having some trouble deciding how best to model my groundwater level data.  I have evaluated it using the ESDA tools and I have a positively skewed non-normal data set with a WNW to ESE global trend.  I have tried a couple of different kriging models and the EBK provides the best overal result in terms of prediction error statistics.  My power function is not between 0.25 and 1.75 as recommended in the help files so I'm wondering what does this mean. Also I'm not entirely sure what my normal QQ plot is telling me- does the line have to be 1:1 or does the slope not matter just as long as the data points fall along the line?

Thanks Simon.

Ps: I also noted there are more options for different semivariogram models in the 10.2 files..I assume these options aren't available in the 10.1 version.