Hi
Well, with indicator a trend means (from my point of view) that there
is some trend in the probability of occurrence
of a given category. If you use a ordinary kriging with a small
neighbor search in some way you already
take into account the trend (i.e. with ok we assume that the mean
proportion of a category changes smoothly with location).
S. T.
At 13.31 08/04/2008, you wrote:
Dear list,
It would be appreciated if someone guide me about how to deal with
the problem of trend in indicator variography and kriging. For
continuous variables, it is more or less clear how to remove such
trends but for categorical variables, what can we do?
Regards
E. R. Khojasteh
You rock. That's why Blockbuster's offering you
<http://us.rd.yahoo.com/evt=47523/*http://tc.deals.yahoo.com/tc/blockbuster/text5.com>one
month of Blockbuster Total Access, No Cost.