Change We Can Believe in: Comparing Longitudinal Network Models on Consistency, Interpretability and Predictive Power

Block, P., Koskinen, J., Hollway, J., Steglich, C., and Stadtfeld, C. (2017). Change we can believe in: Comparing Longitudinal Network Models on Consistency, Interpretability and Predictive Power. Social Networks, Forthcoming

57 Pages Posted: 9 Aug 2017

See all articles by Per Block

Per Block

ETH Zurich

Johan H Koskinen

The University of Manchester

James Hollway

Graduate Institute of International and Development Studies (IHEID)

Christian Steglich

University of Groningen; Linkoping University - Institute for Analytical Sociology (IAS)

Christoph Stadtfeld

ETH Zürich - Department of Humanities, Social and Political Sciences (GESS)

Date Written: August 7, 2017

Abstract

While several models for analysing longitudinal network data have been proposed, their main differences, especially regarding the treatment of time, have not been discussed extensively in the literature. However, differences in treatment of time strongly impact the conclusions that can be drawn from data. In this article we compare auto-regressive network models using the example of TERGMs - a temporal extension of ERGMs - and process-based models using SAOMs as an example. We conclude that the TERGM has, in contrast to the ERGM, no consistent interpretation on tie-level probabilities, as well as no consistent interpretation on processes of network change. Further, parameters in the TERGM are strongly dependent on the interval length between two time-points. Neither limitation is true for process-based network models such as the SAOM. Finally, both compared models perform poorly in out-of-sample prediction compared to trivial predictive models.

Keywords: TERGM, SAOM, social network dynamics

JEL Classification: C18, C32

Suggested Citation

Block, Per and Koskinen, Johan H and Hollway, James and Steglich, Christian and Steglich, Christian and Stadtfeld, Christoph, Change We Can Believe in: Comparing Longitudinal Network Models on Consistency, Interpretability and Predictive Power (August 7, 2017). Block, P., Koskinen, J., Hollway, J., Steglich, C., and Stadtfeld, C. (2017). Change we can believe in: Comparing Longitudinal Network Models on Consistency, Interpretability and Predictive Power. Social Networks, Forthcoming, Available at SSRN: https://ssrn.com/abstract=3014615

Per Block (Contact Author)

ETH Zurich ( email )

Rämistrasse 101
ZUE F7
Zürich, 8092
Switzerland

Johan H Koskinen

The University of Manchester ( email )

Oxford Road
Manchester, N/A M13 9PL
United Kingdom

James Hollway

Graduate Institute of International and Development Studies (IHEID) ( email )

Maison de la Paix
Chemin Eugène-Rigot 2
Geneva, 1211
Switzerland

Christian Steglich

Linkoping University - Institute for Analytical Sociology (IAS) ( email )

Norrköping, 601 74
Sweden

University of Groningen ( email )

P.O. Box 800
9700 AH Groningen, Groningen 9700 AV
Netherlands

Christoph Stadtfeld

ETH Zürich - Department of Humanities, Social and Political Sciences (GESS) ( email )

Weinbergstrasse109
Zurich, Zurich 8092
Switzerland

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
65
Abstract Views
487
Rank
617,745
PlumX Metrics