[GRASSLIST:4082] normal distribution

[Thomas Dewez]

Dear list,

I would like to bounce ideas off the (geo)statisticians among you. It
relates to the normal distribution and p-values.

I created a difference image between two DEM of the same are and would like
to filter out only the outliers. I am a little worried that my thinking is
not correct so feel free to comment.

The difference image is standardized ((obs-mean)/stdev) and I intend to
reject any score larger than +-1.96. How could I test that the difference
image is truly normal so that the threshold is meaningful? Do you reckon
this is a valuable way to proceed to reject values? It is nicely context
sensitive but have I missed something?

I have played a little bit with R under Windows for other reasons. Would
anybody know if this version of R (1.4.1 for Windows) would link with the
geostatistical tool R/Grass?

Thanks for your help

Thomas

_________________________________
Thomas Dewez

PhD research student
Dept Geography & E.S.
Brunel University
Uxbridge, UB8-3PH, Mddx
United Kingdom

office: +44-1895-203215 (x2694)
fax: +44-1895-203217

e-mail: thomas.dewez at brunel.ac.uk
webpage: http://www.brunel.ac.uk/depts/geo/people/thomasdewez.html