2

In the discussion in the accepted answer in this question, user3050574 said that:

"... it is my understanding that mat2listw creates a row standardized weight matrix from a matrix that is currently just in binary form."

This is the only place that I read about this kind of saying. In the "spdep" R document, it is said that

"The function converts a square spatial weights matrix, optionally a sparse matrix to a weight list object, ..."

Does this conversion include row-standardizing?

I have a weight matrix with each element as the exact weight that I want to apply. Therefore it's crucial to me to be certain about whether the mat2listw function generates a row-standardized weight matrix or not.

double-beep
  • 5,031
  • 17
  • 33
  • 41
Teng Huang
  • 21
  • 3

1 Answers1

2

This is puzzling me as well. I also have a weight matrix I want to apply to my estimations. Spml allows to use either a Matrix for weights or a listw. So I tried both and compared the results. It turned out that the estimation with the matrix itself and the listw obtained via mat2listw delivers the same results (I think this supports the idea that mat2listw does not row standardize by default). However when I apply the impacts() function to my output, I get the following error: Error in impacts.splm(b1, listw = lw1) : Only row-standardised weights supported

clusterb8gaxilulu
  • 21
  • 2
  • I know this is from a few years back, but did you ever find a solution to this error? I'm having the identical issue. – Abe Oct 21 '20 at 05:08