Remark 1.

An experimental variogram that is not bounded above (for example the polinomial variogram with $\alpha\ge 1$) implies an infinite variance, and thus the covariance does not exist. Only the intrinsic hypothesis is acceptable. If the variogram achieves a ``sill'' then the phenomenon has a finite variance and the covariance exists.

Figure 2.3: Example of typical spatial correletion structures that may be encountered in analyzing measured data