***** To join INSNA, visit http://www.insna.org *****

Hello Socnetters,

I have a question on the centrality measure. I usually consider the all answers received for structuring the network matrix. However, in large organizations, when I am trying to discovered the most central actor by department, for example, among 20 departments in a company, I can be biased by not considering the weight of those departments with more interviewees. In this case, for instance, five answers from the marketing department could not equal to 15 answers from the finance department, but the most of centrality measure automatically binarizes the data considering 15 answers as one (0 or 1) and therefore, with the same weight of those answers from the marketing department.

So, in this case, I lost the weight of the different branches. I would be pleased if I can get some help on this.

Steven

_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.