Activity Number:
|
433
- SPEED: Applications of Advanced Statistical Techniques in Complex Survey Data Analysis: Small Area Estimation, Propensity Scores, Multilevel Models, and More
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, July 31, 2018 : 2:00 PM to 2:45 PM
|
Sponsor:
|
Survey Research Methods Section
|
Abstract #332650
|
|
Title:
|
Generalized Estimating Equations for Social Network Data
|
Author(s):
|
Miles Ott* and Bjorn Westgard and Brian Martinson and Michael Maciosek
|
Companies:
|
Smith College and HealthPartners and HealthPartners and HealthPartners
|
Keywords:
|
generalized estimating equations;
social network data;
respondent-driven sampling;
correlated data
|
Abstract:
|
The method of using generalized estimating equations (GEE) for correlated response data (both longitudinal and clustered) is widely employed across many disciplines. Social network data tends to have more complicated correlation structures than longitudinal or clustered data. In this paper we introduce GEE for social networks, where we extend the GEE approach to correlation structures based on social network connections, and allow for the incorporation of sampling weights. The proposed method is flexible in that it can be applied to ego network data, respondent-driven sampling data (in which a network is sampled through multiple distinct referral trees), and any network data where there are a sufficient number of unconnected network components. We demonstrate how to use the GEE approach for social networks through simulation studies, and in an analysis investigating risk factors of cardiovascular disease in a sample of Somali Americans in Minneapolis collected through respondent-driven sampling.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2018 program
|