|
Activity Number:
|
127
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Social Statistics Section
|
| Abstract - #304410 |
|
Title:
|
Mixed Models and Q-Connectivity Graphs for Dynamics of Social Interactions
|
|
Author(s):
|
Burcu Eke*+ and Sharon Lohr
|
|
Companies:
|
Arizona State University and Arizona State University
|
|
Address:
|
School of Mathematics and Statistics, Tempe, AZ, 85287-1804,
|
|
Keywords:
|
Social networks ; random effects ; dynamic graphs
|
|
Abstract:
|
Q-connectivity graphs (Barcelo and Laubenbacher, 2005) are a new representation of social interactions that encompass both the frequency and the dynamic nature of the social interactions. These graphs display the social interactions of one actor, called the target actor, over repeated observations. Vertices in a Q-connectivity graph are limited to the individuals interacting with the target actor, and edges are drawn between two vertices if they interact with each other at the same time they interact with the target actor. We propose a two-stage mixed model to summarize information in these graphs. Our model differs from previous work in social networks since we model the dynamic social networks over time, accounting for multiple observations over the same actor. We apply our model to children playmate data.
|
