ASREML: Modelling semivariogram

From: Thomas Bishop <t.bishop_at_USYD.EDU.AU>
Date: Tue, 30 Oct 2007 17:18:18 +1100

 

Dear ASREML Users,

 

I am attempting to use ASREML to analyse spatial data that is from an
observational study rather than a comparative experiment. More
specifically I am trying to fit a geostatistical model based on fixed
effects with the spatial coordinates and fitting of a correlation model
to the spatially correlated residuals. I am interested in the soil
water content. This is basically the same as classical universal
kriging or kriging with trend. I am new to ASREML and am having real
difficulties extracting anything other than the regression coefficients.

 

My sample code based on the recipes of Luis Apiolaza Recipes is:

 

Water

 

      xcoord

      ycoord

      water

Water.txt

 

 

water ~ mu xcoord ycoord !r units

0 0 0 1

0 102 IEUC 0.1

 

 

Any help to fix my code would be appreciated. I just want to extract
the regression coefficients and semivariogram parameters. My data is
attached.

 

Thanks in advance,

 

Tom

 

 

Received on Sat Oct 30 2007 - 17:18:18 EST

This webpage is part of the ASReml-l discussion list archives 2004-2010. More information on ASReml can be found at the VSN website. This discussion list is now deprecated - please use the VSN forum for discussion on ASReml. (These online archives were generated using the hypermail package.)