I have a map of Iowa of with 4000 locations. At each location, I have a
cancer mortality rate. I need to test my null hypothesis; that the spatial
distribution of the mortality rates is random. For this test, I need to
establish a spatial reference distribution.
My reference distribution will be created by some random relabelling
algorithm. The 4000 locations would remain fixed, but the observed
mortality rates would be randomly redistributed. Then, I want 1000
permutations of the same algorithm. For each of those 1000 times, I would
record the redistributed mortality rate at each location. Then, I would
calculate the mean of the 1000 points. The result would be a spatial
reference distribution with a mean value of the random permutations at each
of the 4000 locations.
Thanks for the response,
Kevin
On Wed, Apr 20, 2011 at 11:08 AM, John Kane <jrkrid...@yahoo.ca> wrote:
> Can you explain this a bit more. At the moment I don't see what you are
> trying to achieve. "calculate the mean of the 1000 values at each of the
> 4000 points" does not seem to make sense.
>
> --- On Wed, 4/20/11, kmatthews <kevin-matth...@uiowa.edu> wrote:
>
> > From: kmatthews <kevin-matth...@uiowa.edu>
> > Subject: [R] Random Relabelling
> > To: r-help@r-project.org
> > Received: Wednesday, April 20, 2011, 10:04 AM
> > I have 4000 observations that I need
> > to randomly relabel 1000 times and then
> > calculate the mean of the 1000 values at each of the 4000
> > points. Any ideas
> > for where to begin?
> >
> > Thanks
> > Kevin
> >
>
>
[[alternative HTML version deleted]]
______________________________________________
R-help@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.
