[R] determination of the number of lags

Ole Christensen o.christensen at lancaster.ac.uk
Tue May 28 13:10:36 CEST 2002


Dear Celine

To my knowledge there is no ``correct'' way to construct an empirical
variogram. 

Recommandations

1. max.dist = 0.5 * max dist between pairs of locations. Because the
variogram starts becoming unstable at larger distances.

2. Make sure that you have sufficient number of pairs at each lag (say,
200).

I would play a bit around with the specification of lags to see how much
the variogram depended on the choice of lags.

Ole

CELINE RONDEY wrote:
> 
> Dear all,
> 
> I wish use the "est.variogram" function under R.
> My question concerns the determination of number of lags.
> 
> To make this calculation, i determined the biggest and the smallest
> distance between 2 pairs of points.
> I built the following tolerance : tol=mindistance/2 and i defined 1 lag as
> : 1lag=mindist+tol.
> Then i made a buckle the step of stop of which the maximal distance.
> But, i don't known if this method is correct.
> 
> So, my question is :
> How to determine num.lag correctly?
> 
> Thanks in advance for all kind of help.
> 
> Céline RONDEY
> 
> -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
> r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
> Send "info", "help", or "[un]subscribe"
> (in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
> _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

-- 
Ole F. Christensen
Department of Mathematics and Statistics
Fylde College, Lancaster University 
Lancaster, LA1 4YF, England
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._



More information about the R-help mailing list