Create spatial weighting matrix for cities belonging to the same administrative area

[Xinchen Dai]

I am a beginner in spatial analysis. I am trying to create a spatial weighting matrix that cities belonging to the same administrative area have value one and zero otherwise. Is it possible to do it with spmat?

[Nick Cox]

Cross-posted at https://stackoverflow.com/questions/...administrative

[Mike Lacy]

Solving your problem would depend completely on the structure and coding of your data. If you post a sample of your data using -dataex- as described in the StataList FAQ, your chance of receiving a helpful response would improve considerably.

[Xinchen Dai]

Cross-posted at https://stackoverflow.com/questions/...administrative

Sorry, I was not aware of the rule and will delete the post at Stack Overflow. After several trials, I think it's probably the easiest to prepare the matrix in excel with its transpose function.

[Mike Lacy]

The OP apparently has a satisfactory solution for their purposes, but to help people with a similar problem who might encounter this thread in the future, I'd note that solving this in Stata would likely be easy, i.e., a few lines of code. For example, transposing matrices in Stata (data sets, Stata matrices, or Mata matrices) is trivial, documentation about which can be found via -help transpose-.

[Nick Cox]

It's not a rule that you can't cross-post. There is just a request that you tell us about cross-posting.

Being new here is precisely why you should read the FAQ Advice, as prompted generally and as recommended by Mike Lacy. See https://www.statalist.org/forums/help

[Xinchen Dai]

It's not a rule that you can't cross-post. There is just a request that you tell us about cross-posting.

Being new here is precisely why you should read the FAQ Advice, as prompted generally and as recommended by Mike Lacy. See https://www.statalist.org/forums/help

Thanks for the link!

[Xinchen Dai]

Solving your problem would depend completely on the structure and coding of your data. If you post a sample of your data using -dataex- as described in the StataList FAQ, your chance of receiving a helpful response would improve considerably.

Hello, Mike, this is a matrix showing to which province each city belongs:

* Example generated by -dataex-. To install: ssc install dataex
clear
input float(city prov1 prov2 prov3)
1 1 0 0
2 1 0 0
3 1 0 0
4 0 1 0
5 0 1 0
6 0 1 0
7 0 1 0
8 0 0 1
9 0 0 1
end

What I want to create is the following:

* Example generated by -dataex-. To install: ssc install dataex
clear
input float(city city1 city2 city3 city4 city5 city6 city7 city8 city9)
1 1 1 1 0 0 0 0 0 0
2 1 1 1 0 0 0 0 0 0
3 1 1 1 0 0 0 0 0 0
4 0 0 0 1 1 1 1 0 0
5 0 0 0 1 1 1 1 0 0
6 0 0 0 1 1 1 1 0 0
7 0 0 0 1 1 1 1 0 0
8 0 0 0 0 0 0 0 1 1
9 0 0 0 0 0 0 0 1 1
end

A city-by-city matrix, where cities belonging to the same provinces have value 1. I think what I need to do is transpose by row. Is there a good way to accomplish this task in Stata?