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

I’m reviewing a paper in which the authors measure two social network relations between work colleagues: friendship (“who do you see socially outside of work”) and advice (“who do you go to if you face a situation or problem at work and you need advice”). They used name generators (yes/no dichotomy) and are assessing out-degree centrality. 

Apparently, they saw relatively few reports of each relationship: out of over 300 participants, there was an average of about 3 ties per relation, and they struggled to find significant results. Due to this low base rate, they decided to aggregate the two items into one overall network measure for out-degree centrality.

I’d love to hear your thoughts on justifying this procedure of combining two separate network items (it seems more data driven than theoretical, but they make some reasonable conceptual arguments). Have other studies done so? It seems that, qualitatively, the network generators are asking about connections you “interact with” inside of work versus outside of work, with somewhat of an expressive/instrumental comparison.

Much appreciated,

Jessica R. Methot, PhD
Assistant Professor of Human Resource Management
School of Management and Labor Relations
Janice H. Levin Bldg., Room 209
Rutgers University
94 Rockafeller Road, Livingston Campus
Piscataway, NJ 08854
office: (848) 445-1112
[log in to unmask]

_____________________________________________________________________ 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.