Spatial partitioning of direct, indirect and total impacts (2)

Dear list members,

I am sorry that I am going to repeat my question. I do not want to insist,
but since I sent it right before the weekend, the timing was probably not
so good and I thought it would be good to give it a second chance.

I am trying to reproduce table 2.1 (p. 41) of LeSage and Pace (2009).

This is a table containing the direct, indirect and total impacts of a SAR
model (since the regression coefficients cannot be interpreted directly
because of spillovers), *partitioned by W-order*.

I am able to produce the first part of the table ( impacts() in R ), but
for the moment I don't have a clue on *how to split these impacts per power
of W*. I would like to do this both for a SAR and for a SDM model.

Please, could somebody give me a hint on how to do this? I would be very
grateful!

Thank you very much in advance,

Janka

	[[alternative HTML version deleted]]