s-news
[Top] [All Lists]

Re: [S] calculating empirical semivariograms

To: Paul Schwarz <Paul.Schwarz@cornell.edu>
Subject: Re: [S] calculating empirical semivariograms
From: Prof Brian D Ripley <ripley@stats.ox.ac.uk>
Date: Thu, 28 Sep 2000 07:47:07 +0100 (BST)
Cc: s-news@wubios.wustl.edu
In-reply-to: <002f01c028e4$5c364950$600b1818@twcny.rr.com>
Sender: owner-s-news@wubios.wustl.edu
On Wed, 27 Sep 2000, Paul Schwarz wrote:

> 
> S-News readers,
> 
> I'm interested in learning about the algorithms used to compute
> empirical or sample semivariograms.  I have S+SpatialStats, for example,
> so I have the means for calculating empirical semivariograms.  I also
> understand the basic formula
> 
>   gamma(h) = 0.5*N(h)*sum(Zi - Zj)^2
> 
> used for estimating the semivariogram where h = i - j is the Euclidean
> distance or "lag" and N(h) is the number of data pairs.  So my interest
> is in learning about how to do these calculations in S-PLUS so that I
> can experiment with other approaches for estimating these kinds of
> statistics.  I am assuming that there are some relatively efficient ways
> to do these calculations using vectors and matrices.  If anyone has
> written code to do this in S-PLUS that they wouldn't mind sharing, I
> would be grateful.

Only relatively efficient.  Early versions of my spatial library had
pure S versions, but the C versions are several times faster and use much
less memory.  Assuming that you are happy handling C code, you can start
with those programs (part of the VR suite).

-- 
Brian D. Ripley,                  ripley@stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu.  To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message:  unsubscribe s-news

<Prev in Thread] Current Thread [Next in Thread>