The final exercise is to generate data from a Gaussian random field 
with an exponential covariance function, estimate the parameter, 
and compare estimation using likelihood with that using 
least squares. You may want  to generate the data at the same points
as the Parana data set in geoR. 
You decide how many replications to do, and what criteria of comparison to use.


I suggest working in groups of two or three. 

The following functions may be useful:
grf		simulates a Gaussian random field
variofit	estimates parameters using least squares
likfit		estimates parameters using likelihood
krige.bayes	estimates parameters using Bayesian methods

There are also plotting tools, such as 
plot.grf 		plots variogram from grf simulations
lines.variomodel.* adds appropriate (according to *) variogram lines to 			
			plots