Maybe I need express my question again: In n points of observation, we gain X(x1, x2, ..., xn), Y(y1, y2, ..., yn) and Z(z1, z2,..., zn). We want to calculate the similarity among X, Y and Z.
This question is very general. There are certain distance measures like euclidean distance or Manhattan distance that describe how close/similar certain data points are in multivariate space (and which are the basis of classifying, clustering etc. approaches).
I propose you the use of multivariate structural analysis using cross-semivariograms. Using the semivariograms you can obtain the similarity degree considering different distances (lags). Also if you data has an anisotropic behaviour you can obtain directional variograms in order to characterise this phenomenon.
Any basic geostatistical book can be useful for you. You only need that the available data has spatial coordinate (time or space) and your variable data. It is possible the correlation if you have any "no data" points.
- Badges
- Science topic
- Similar topics
- Geoscience
- Geoinformatics