Dear list:

I have the following sampling problem. Given a rectangular regular grid of
c columns and r rows (say 10*10), consisting of c*r cells of equal size. I
want to chose n cells (say 15 out of 100 cells), which can be  interpreted
as samples with support equalling the size of one cell, taken from a
regular grid of grid distance = cell size. 
According to which pattern do I have to pick the samples (i.e. which cells
do I have to chose) in order to get a frequency distribution of distances
between the centres of the cells (n*(n-1)/2 distances = pairs of cells =
105 in the example) which is as close as possible to uniform, i.e. all
distances occur with about the same probability ?

I tried to solve it numerically, which results in quite strange looking
sampling patterns. 

Trying all combinations (r*c over n = 2.53E17 in the example, if I
calculated correctly), is obviously tedious if r,c and n become large. Are
there any analytical solutions ? Any literature about this ?

Thanks for hints,
Peter


-----------------------------------------------------
Peter Bossew 

European Commission (EC) 
Joint Research Centre (JRC) 
Institute for Environment and Sustainability (IES) 

TP 441, Via Fermi 1 
21020 Ispra (VA) 
ITALY 
  
Tel. +39 0332 78 9109 
Fax. +39 0332 78 5466 
Email: [EMAIL PROTECTED] 

WWW: http://rem.jrc.cec.eu.int 
  
"The views expressed are purely those of the writer and may not in any
circumstances be regarded as stating an official position of the European
Commission."

 


+
+ To post a message to the list, send it to [email protected]
+ To unsubscribe, send email to majordomo@ jrc.it with no subject and 
"unsubscribe ai-geostats" in the message body. DO NOT SEND 
Subscribe/Unsubscribe requests to the list
+ As a general service to list users, please remember to post a summary of any 
useful responses to your questions.
+ Support to the forum can be found at http://www.ai-geostats.org/

Reply via email to