Social Statistics Seminar Series - Jackie Wong Siaw Tze
Dates: | 8 April 2025 |
Times: | 14:00 - 15:30 |
What is it: | Seminar |
Organiser: | School of Social Sciences |
Who is it for: | University staff, External researchers, Adults, Alumni, Current University students, General public |
Speaker: | Jackie Wong Siaw Tze |
|
Fully Bayesian Estimation of Temporal Decay in Ordinal Relational Event Models
Relational event models (REMs) can infer the generative properties of longitudinally observed social networks with instantaneous edges. They assume conditional independence of edges given sufficient network statistics formed over the past event sequence. A popular specification in REMs is to subject these statistics to exponential temporal decay with a fixed half-life parameter to attribute higher importance to more recent edge events in the formation of network statistics. Assuming a fixed halflife parameter may cause biased estimates and obfuscates the temporal horizon over which network effects operate in empirical social systems. In this talk, we will briefly discuss these limitations, and address them by proposing fully Bayesian estimation of REMs, with the half-life parameter designated as an estimable quantity. A “pre-computation” strategy is devised to speed up calculations for practical feasibility of the sampling procedure. The approach is adapted to discourse network analysis, which models political actors' statements about their preferred policy beliefs as dynamic networks. An application to the policy debate on reforming the German public pension system illustrates how temporal decay for inertia, actor activity, belief popularity, and actor homophily can be
estimated alongside the main coefficients. We provide convergence diagnostics, an illustration of bias correction relative to fixed parameters, discuss stabilisation using hyper-parameters, and extend the approach to include both Breslow's and Efron's methods for breaking ties in the event sequence.
Speaker
Jackie Wong Siaw Tze
Role: Lecturer in Actuarial Science
Organisation: University of Essex
Travel and Contact Information
Find event
Arthur Lewis_2.016/2017 Boardroom
Arthur Lewis Building