Dear colleagues,
I am trying to group observations based on their (possibly indirect) connections . For example, imagine workers may have worked at different branches and the following is their working history (not time sensitive).
Code:
clear
input personid branchid
1 1
2 1
1 2
3 2
3 3
4 3
5 4
6 4
end
The goal is to generate a new variable (group) that yields the following.
personid branchid group
1 1 1
2 1 1
1 2 1
3 2 1
3 3 1
4 3 1
5 4 2
6 4 2
The logic is that personal 1 is directly connected to person 2 (they both worked at branch office 1) and also to person 3 (they both worked at branch office 2), and indirectly connected to person 4 (because 3 and 4 both worked at branch office 3), hence persons 1-4 shall all belong to the same group. Similarly for person 5 and 6 as another group. Any comments on how to code and generate the group would be greatly appreciated!
Thanks.
Hua
Related Posts with Group observations with indirect tie.
Exporting regression results to a Word documentHi all, I'll be very happy if you can help me. I'm trying to export the results of multiple regress…
Promotion ProblemsThe summary of this post is that (a) replace, nopromote functions differently on string variables th…
rounding to 0.5, 1.5, 2.5, 3.5 etcHello, I have a question in regard to rounding. As an example I have a data like this: Code: list …
need urgent helpI tried to do heteroskedasticity test for panel-level data by using the commands from the site menti…
Generated regressor problem and bootstrapping?Hello, I have the fitted values of a regression to be used as a regressor for another set of regres…
Subscribe to:
Post Comments (Atom)
0 Response to Group observations with indirect tie.
Post a Comment