but I would recommend performing an indicator transform of

your data before starting the (cross) variogram analysis.

For each class, you can define an indicator of occurrence

of that class at any location u; e.g. for your classes

1 (0-10) and 2 (10-20):

I(u;c_1)=1 if 0 < z(u) <= 10, and I(u;c_1)=0 otherwise

I(u;c_2)=1 if 10 < z(u) <= 20, and I(u;c_2)=0 otherwise

Then, you compute a semivariogram of these indicators:

g(h,c_1) = (1/2N(h)) sum_alpha=1^N(h) [i(u_alpha;c_1)-i(u_alpha+h;c_1)]^2

or cross semivariogram

g(h,c_1,c_2) = (1/2N(h)) sum_alpha=1^N(h)

[i(u_alpha;c_1)-i(u_alpha+h;c_1)] x

[i(u_alpha;c_2)-i(u_alpha+h;c_2)]

The indicator variogram (=twice the value of the semivariogram 2g(h,c_1))

measures how often two locations a vector h apart belong to c_1

and another category. The smaller 2g(h,c_1), the better the spatial

connectivity of the class c_1. The cross variogram (2g(h,c_1,c_2))

measures the transition frequency between c_1 and c_2.

Cross indicator semivariograms can be computed using the public-domain

gslib programs that can be downloaded from

http://www.ualberta.ca/~smpe/people/clayton/software.html

Examples of class indicator variograms can be found in the paper:

Goovaerts, P. 1996.

Stochastic simulation of categorical variables using a classification

algorithm and simulated annealing.

Mathematical Geology, 28(7):909--921.

There is also a research report (SCRF 94 paper) that you can download

from my webpage.

If you want to invest more time in the use of

indicator variograms to detect different types

of processes (e.g. mosaic, diffusion-type..), two

references are:

Rivoirard (1993). Relations between the indicators related to a

regionalized variable. In: Soares, A. (Ed.), Geostatistics Tr\'oia '92,

Kluwer Academic Publishers, Dordrecht, pp. 273--284.

Webster R, Boag B (1992) Geostatistical analysis of cyst nematodes

in soil. J. Soil Sci. 43: 583--595

Regards,

Pierre

<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>

________ ________

| \ / | Pierre Goovaerts

|_ \ / _| Assistant professor

__|________\/________|__ Dept of Civil & Environmental Engineering

| | The University of Michigan

| M I C H I G A N | EWRE Building, Room 117

|________________________| Ann Arbor, Michigan, 48109-2125, U.S.A

_| |_\ /_| |_

| |\ /| | E-mail: goovaert@...

|________| \/ |________| Phone: (734) 936-0141

Fax: (734) 763-2275

http://www-personal.engin.umich.edu/~goovaert/

<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>

On Wed, 5 May 1999, nowook park wrote:

> Dear all..

>

> I have some question about cross variogram analysis..

>

> in geoscience data integration scheme,

> for the purpose of the evaluation of quantitative spatial influences of

> each data layer to integrated layer.

> if I perform cross variogram analysis with respect to

> classified data, not continous data,

> (ex) class 1 : 0 ~ 10 , class 2 : 10 ~ 11 etc..

> control variable : integrated layer , target variable : each input

> layer)

> is it reasonable ? or is it useless ?

> I wonder whether application to the classified data of cross variogram

> is valid, or not..

> also,if the grid cell size is 30m * 30m,

> what is the reasonable unit lag interval w.r.t. sampling space?

>

> If anyone has cross variogram fortran codes,

> please let me know..

>

> Thank you..

>

> best regards,

>

> nowook..

>

>

> --

> *To post a message to the list, send it to ai-geostats@....

> *As a general service to list users, please remember to post a summary

> of any useful responses to your questions.

> *To unsubscribe, send email to majordomo@... with no subject and

> "unsubscribe ai-geostats" in the message body.

> DO NOT SEND Subscribe/Unsubscribe requests to the list!

>

--

*To post a message to the list, send it to ai-geostats@....

*As a general service to list users, please remember to post a summary

of any useful responses to your questions.

*To unsubscribe, send email to majordomo@... with no subject and

"unsubscribe ai-geostats" in the message body.

DO NOT SEND Subscribe/Unsubscribe requests to the list!