Consider two random variables and
, at two points
and
separated by the vector
.
The variability between these two quantities is
characterized by the variogram function
In all generality, this variogram
is a function of both the point
and the vector
. Thus, the estimation of this variogram requires several
realizations,
of the pair of random variables
.
Now, in practice, at least
in mining applications, only one such realization
is available and this is the actual measured
couple of values at points
and
.
To overcome this problem, the intrinsic hypothesis
is introduced.
This hypothesis is that the variogram function
depends only on the separation vector
(modulus and direction) and
not on the location
. It is
then possible to estimate the variogram
from the available data: an
estimator
is the arithmetic mean of the squared differences
between
two experimental measures
at any two points separated by the vector
; i.e.,
Note that the intrinsic hypothesis is simply the hypothesis of second-order
stationarity of the differences
.
In physical terms,
this means that, within the zone D, the structure of the variability between
two grades
and
is constant and,
thus, independent of x; this
would be true, for instance, if the mineralization within D were
homogeneous.
The intrinsic hypothesis is not as strong as the hypothesis of stationarity
of the random function itself. In practice, the intrinsic hypothesis can
be reduced, for example, by limiting it to a given locality; in such a case,
the function
can be expressed as two terms:
where
is an intrinsic variability constant over the
zone D and
characterizes an intensity of variability which depends on the locality
x, cf.
the concept of proportional effect.
A typical form of a variogram may be seen in Figure 1.2. Here of
course, a direction has been chosen and fixed, such that it is possible to plot
the variogram depending on the absolute value only. The
crosses represent the empirical values and the drawn
curve is for a stylized form of an estimated variogram model.