Activity Number:
|
333
- SPEED: Biopharmaceutical Statistics, Medical Devices, and Mental Health
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 1, 2017 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Social Statistics Section
|
Abstract #322784
|
|
Title:
|
Survival Analysis on a Social Network
|
Author(s):
|
SONG Fangda* and Yingying Wei
|
Companies:
|
The Chinese University of Hong Kong and The Chinese University of Hong Kong
|
Keywords:
|
Social network ;
Bayesian survival analysis ;
Frailty model ;
MCMC ;
Semi-parametric model
|
Abstract:
|
There has been extensive research on social networks in the past decade. Nevertheless, most methods analyze relational data that are in the format of binary or categorical data. In contrast, in this paper, we study a scenario where sequences of survival data are observed for some pairs of nodes. We build a Bayesian semi-parametric frailty model to simultaneously learn the network structure and estimate the survival function for each pair of nodes. An MCMC algorithm is developed to conduct posterior inference, and its performance is evaluated via simulation studies. We apply the proposed model to study the email response time among employees in a company. The obtained results provide novel insights on the company organization and power relations.
|
Authors who are presenting talks have a * after their name.