A. Lorenzo Arribas
We evaluate causal inference methodologies with a focus on understanding effects of potential interventions and policy scenarios in facilitating behaviour changes that accelerate green recovery to move society towards a circular economy. Traditional statistical approaches fail to capture causal relationships and resulting feedbacks, whilst agent-based modelling which can represent explicit causal relations are problematic when used for inference. Causal inference is well established in other disciplines such as epidemiology and is a growing area in economics. In circular economy applications, tailored causality frameworks have been used sparingly but there is a recognised need to reflect causality more formally. We build on previous work assessing the potential of causal inference methods and assess the feasibility of new methods to estimate causal effects for observational data by means of an application to data on circular economy behaviours.
Palabras clave: Causal Inference; Circular Economy; Observational Data.
Programado
Sesión Invitada Royal Statistical Society
9 de junio de 2022 10:10
Sala Audiovisuales
