Closed rlsandovalp closed 1 year ago
There are different formulations of the gaussian covariance model that basically only differ by the rescale factor and this was also the reason why we added the scaling factor.
We choose this factor so the length scale actually matches the integral scale of the model.
If you want the formulation of webster, just set s=1
.
Hi,
Just wondering why the Gaussian variogram differs from the equation written by Webster (2007).
There, the equation reads $\gamma (h) = c\left(1-\exp\left(-\frac{h^2}{r^2}\right)\right)$
However, in the covmodels file it is written as
$\gamma(h)= c \left(1-\exp\left(-\left(s\cdot\frac{h}{r}\right)^{2}\right)\right)$
Where the standard rescale factor is $s=\frac{\sqrt{\pi}}{2}$.