Skip to content

Toggle service links

You are here

  1. Home
  2. Statistics Seminar - Causal analysis with Chain Event Graphs

Statistics Seminar - Causal analysis with Chain Event Graphs

Dates
Tuesday, June 7, 2022 - 14:00 to 15:00

Speaker: Xuewen Wu (Warwick University)
  
Abstract: Graph-based causal inference has recently been successfully applied to explore system reliability and to predict failures in order to improve systems. One popular causal analysis following Pearl and Spirtes et al. to study causal relationships embedded in a system is to use a Bayesian network (BN). However, certain causal are difficult to express fully through a BN. Our recent work demonstrated the flexibility of using a Chain Event Graph (CEG) instead to capture causal reasoning embedded within engineers' reports. The CEG is derived from an event tree and can flexibly represent the unfolding of the asymmetric processes. The semantics of the CEG are expressive enough to capture the necessary intervention calculus. Through developing the bespoke causal algebras we can use the CEG framework to make predictive inferences about the effects of various types of maintenance. Back-door theorem can be adapted to apply to these interventions to help discover when causal effects can be identified from a partially observed system.