Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It only takes a minute to sign up.
Sign up to join this community
Our lab used to have a program called GS+ that let us make semi variograms on our data and analyse them. Unfortunately, the licence has expired.
Is there another piece of software that lets you do this? If so, how specifically? We prefer a free and open source licence, but all suggestions are welcome.
Besides R, here are a few links that may be of interest that do not appear to be on the AI Geostats page:
The book, A Practical Guide to Geostatistical Mapping, has relevent examples using R and Google Earth (of course R is used to estimate the variograms).
The most comprehensive list has long been maintained at the AI Geostats pages: it includes freeware and commercial software (almost 30 free ones). That page has a separate link to add-ons, such as any R packages.
AFAIK, there is no R package for handling 3D variography or change of support problems. The R packages are also weak at modeling rich datasets, which often need nested models with varying anisotropy and variogram shapes. For good integration of variography, kriging, simulation, EDA, and statistical modeling, though, the R packages are excellent.
package geoR for R could be what you're looking for. From the documentation:
"function variogram Computes sample (empirical) variograms with options for the classical or robust estimators. Output can be returned as a binned variogram, a variogram cloud or a smoothed variogram. Data transformation (Box-Cox) is allowed. “Trends” can be specified and are fitted by ordinary least squares in which case the variograms are computed using the residuals."
Also variofit: "Estimate covariance parameters by fitting a parametric model to a empirical variogram. Variograms models can be fitted by using weighted or ordinary least squares."
There are more geostatistical packages in R.
The R program is free and open source, there are functions in the nlme package for R that do semi-variograms (and probably other options as well, but nlme came up in a quick search).
