Analysis of spatial dependence

After the appropriate spatial sample has been chosen, the next step is to determine whether spatial dependencies exist between the data, and to which extent. There are several methods to do this. The two which will be presented in the following section are:

• The variogram, or explorative variography, respectively
• "Moving window" statistics

Why do we have to worry about spatial dependencies at all? Is it not enough to have an accurate sample? No! Without spatial relationships between our samples we cannot make a statement about the points where no samples were taken. This goes back to a statement by Waldo Tobler, which is known as the "1st law of geography":

"(...) the first law of geography: everything is related to everything else, but near things are more related than distant things." (Tobler 1970)

In most cases, this legality is indeed true. However, we should not rely on it blindly, especially not while standing on the edge of a cliff...