Open guiblanchet opened 9 months ago
Hi Guillaume, I will correct but are you sure that you need row standardization (i.e., style = "W") ? If you want to keep weights untransformed, style should be "B"
Cheers
You are right ! Using style="B" would be better.
This is a slightly tricky problem because, if I run the first line of the example code of the
aem.time
function :There is the following warning :
Warning messages: 1: In mat2listw(mat01) : style is M (missing); style should be set to a valid value 2: In mat2listw(mat01) : no-neighbour observations found, set zero.policy to TRUE; this warning will soon become an error
But there are no error. However, when calling the object
out
, there is the following error message :Error in print.listw(x) : regions with no neighbours found, use zero.policy=TRUE
After a bit of digging and some clarification from https://github.com/r-spatial/spdep/issues/136, found that the warnings and error can be solved by changing L134 of the
aem.time
function fromlw <- mat2listw(mat01)
to
lw <- mat2listw(mat01, style = "W", zero.policy = TRUE)