This is partly an R question, partly a "how do you do it by hand"
question--meaning I would be happy for either.
What I am trying to do is slightly unconventional, so please bear with me.
I do not have a spatial contiguity/weights matrix or a shape file. What I
do have, however, is the value of interest at a specific geographic
location as well as those values for its 4 neighboring locations. There
are no weights for neighbors--they should all be equally weighted--let's
say "1" for the sake of simplicity.
With this information, it *should* be possible to calculate a value for
local Moran's I. Similarly, I think it should be possible to plot the
relationship of the value at this location to those of its immediate
neighbors using a Moran scatterplot, since that is essentially a graph of
spatial lag v. actual value.
However, while I think it should be possible, I have no idea how to do it.
Could I calculate Moran's I or plot a Moran scatterplot using R given the
information I have given? If not, could any spatial statistics gurus
suggest how to calculate it "by hand"? In the latter case, I will
ultimately implement it in R, but knowing how to do it by hand would allow
me to write the pseudocode first.
Thanks,
Lily
[[alternative HTML version deleted]]
_______________________________________________
R-sig-Geo mailing list
R-sig-Geo@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
