kriging to determine effect of area size on global Moran index

Dear bloggers,

I am working with spatial polygons to see how variables are spatially correlated and how such correlation changes in time in a specific country.
I want to look a bit more into detail at Moran?sI and how the morphology (surface and/or population) of the areas I consider can impact spatial correlation.
What I want to do is use my shape file of spatial polygons and divide all the areas in it into a grid of equally surfaced areas (let?s say each area has a surface of 100sqkm).
The resulting grid of areas will have (I think) new centroids and each variable will have to be recomputed (or interpolated) to reflect the new subdivision.

I know kriging should be the ideal tool to do this, but on internet I have found so many tutorials and I am quite confused on the steps to take (also because trying to run the code in my case does not work).

Any help on the matter is greatly appreciated!

Ale