[R-sig-Geo] gamma from fitVariogram output vs. Covariance matrix

[Hodgess, Erin]

Hello everyone:

I have a question about the gamma output which appears with the fitVariogram results, please.

Here is a sample output:
$ exp_var  :Classes ‘gstatVariogram’ and 'data.frame': 12 obs. of  6 variables:
  ..$ np     : num [1:12] 181 499 844 1758 2356 ...
  ..$ dist   : num [1:12] 22.4 52.2 85.4 126.4 176.9 ...
  ..$ gamma  : num [1:12] 116033 138020 133462 133186 134257 ...
  ..$ dir.hor: num [1:12] 0 0 0 0 0 0 0 0 0 0 ...
  ..$ dir.ver: num [1:12] 0 0 0 0 0 0 0 0 0 0 ...
  ..$ id     : Factor w/ 1 level "var1": 1 1 1 1 1 1 1 1 1 1 ...


And you notice there are 12 values.  However, there are 1000 values in the actual data set itself. I realize that there are point-pairs selected in order to produce the gamma values.  But how would this relate to either a covariance or correlation matrix, please?

Thanks in advance,
Sincerely,
Erin




Erin M. Hodgess
Associate Professor
Department of Mathematics and Statistics
University of Houston - Downtown
mailto: hodgesse at uhd.edu

	[[alternative HTML version deleted]]