I see nothing here to do with the 'bootstrap', which is sampling with
replacement.
Do you know what you mean exactly by 'randomly sample'? In general the
way to so this is to sample randomly (uniformly, whatever) and reject
samples that do not meet your restriction. For some restrictions there
are more efficient algorithms, but I don't understand yours. (What are
the 'rows'? Do you want to sample rows in space or xy locations? How
come 'dist' is not symmetric?) For some restrictions, an MCMC sampling
scheme is needed, the hard-core spatial point process being a related
example.
On Wed, 3 Sep 2008, Grant Gillis wrote:
> Hello List,
>
> I am not sure that I have the correct terminology here (restricted
> bootstrap) which may be hampering my archive searches. I have quite a
large
> spatially autocorrelated data set. I have xy coordinates and the
> corresponding pairwise distance matrix (metres) for each row. I would like
> to randomly sample some number of rows but restricting samples such that
the
> distance between them is larger than the threshold of autocorrelation. I
> have been been unsuccessfully trying to link the 'sample' function
to values
> in the distance matrix.
>
> My end goal is to randomly sample M thousand rows of data N thousand times
> calculating linear regression coefficients for each sample but am stuck on
> taking the initial sample. I believe I can figure out the rest.
>
>
> Example Question
>
> I would like to radomly sample 3 rows further but withe the restriction
that
> they are greater than 100m apart
>
> example data:
> main data:
>
> y<- c(1, 2, 9, 5, 6)
> x<-c( 1, 3, 5, 7, 9)
> z<-c(2, 4, 6, 8, 10)
> a<-c(3, 9, 6, 4 ,4)
>
> maindata<-cbind(y, x, z, a)
>
> y x x a
> [1,] 1 1 1 3
> [2,] 2 3 3 9
> [3,] 9 5 5 6
> [4,] 5 7 7 4
> [5,] 6 9 9 4
>
> distance matrix:
> row1<-c(0, 123, 567, 89)
> row2<-c(98, 0, 345, 543)
> row3<-c(765, 90, 0, 987)
> row4<-c(654, 8, 99, 0)
>
> dist<-rbind(row1, row2, row3, row4)
>
> [,1] [,2] [,3] [,4]
> row1 0 123 567 89
> row2 98 0 345 543
> row3 765 90 0 987
> row4 654 8 99 0
>
> Thanks for all of the help in the past and now
>
> Cheers
> Grant
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
--
Brian D. Ripley, ripley at 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 272866 (PA)
Oxford OX1 3TG, UK Fax: +44 1865 272595