***** To join INSNA, visit http://www.insna.org *****
Imagine you have a system composed of several elements and its relationships. In order to identify the natural clusters (modules) of such system: What kind of UCINET measures do you think is the most suitable one? By natural cluster/module I'm referring to a non-technical definition, is about the blocks/clusters/modules that can be visually identified at first sight from Netmap. A fuzzy non-definition, I know...
For few relationships, BICOMPONENTS: Network-Regions-Bicomponents, gives good results, but it doesn't for dense networks.
I have also tried with FACTIONS: Network-Subgroups-Factions, it gives better results than the previous, but it still doesn't fully convince me.
Has anybody been dealing with such or a similar problem?
The second question: In the case of directed graphs and valued (non-binary) relationships, which measure do you think can be the most suitable one?
Best regards and thank you,
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.