Journal article
Latent space models for dynamic networks with weighted edges
Social networks, Vol.44, pp.105-116
01/2016
DOI: 10.1016/j.socnet.2015.07.005
Abstract
•Extensions are given for weighed networks via link functions and data augmentation.•Our models can handle temporal, directed, weighted dyadic data.•Details are given for count and non-negative continuous dyadic data.•We analyze simulated data, mobile phone call log data, and world export/import data.
Longitudinal binary relational data can be better understood by implementing a latent space model for dynamic networks. This approach can be broadly extended to many types of weighted edges by using a link function to model the mean of the dyads, or by employing a similar strategy via data augmentation. To demonstrate this, we propose models for count dyads and for non-negative real dyads, analyzing simulated data and also both mobile phone data and world export/import data. The model parameters and latent actors’ trajectories, estimated by Markov chain Monte Carlo algorithms, provide insight into the network dynamics.
Details
- Title: Subtitle
- Latent space models for dynamic networks with weighted edges
- Creators
- Daniel K Sewell - Department of Biostatistics, University of Iowa, 145 N. Riverside Dr., Iowa City, IA 52242, USAYuguo Chen - Department of Statistics, University of Illinois at Urbana-Champaign, 725 S. Wright Street, Champaign, IL 61820, USA
- Resource Type
- Journal article
- Publication Details
- Social networks, Vol.44, pp.105-116
- Publisher
- Elsevier B.V
- DOI
- 10.1016/j.socnet.2015.07.005
- ISSN
- 0378-8733
- eISSN
- 1879-2111
- Grant note
- DMS-1106796; DMS-1406455 / National Science Foundation (http://dx.doi.org/10.13039/100000001)
- Language
- English
- Date published
- 01/2016
- Academic Unit
- Biostatistics; Public Policy Center (Archive)
- Record Identifier
- 9983997338902771
Metrics
53 Record Views