Inference on Causal Effects of Interventions in Time using Gaussian Processes

TL;DR

This paper introduces Gaussian Process-based non-parametric models for causal inference in time series, enhancing flexibility and uncertainty quantification in assessing intervention impacts, demonstrated through a UK vaccination case study.

Contribution

It develops novel Gaussian Process-based structural time series models for causal inference, extending existing methods with greater flexibility and Bayesian uncertainty estimation.

Findings

Effective modeling of intervention effects over time

Flexible non-parametric approach with uncertainty quantification

Successful application to UK vaccination impact case study

Abstract

This paper focuses on drawing inference on the causal impact of an intervention at a specific time point, as manifested in an outcome variable over time. We operate on the interrupted time series framework and expand on approaches such as the synthetic control (Abadie 2003) and Bayesian structural time series (Brodersen et al 2015), by replacing the underlying dynamic linear regression model with a non-parametric formulation based on Gaussian Processes. The developed models possess a high degree of flexibility posing very little limitations on the functional form and allow to incorporate uncertainty, stemming from its estimation, under the Bayesian framework. We introduce two families of non-parametric structural time series models either operating on the trajectory of the outcome variable alone, or in a multivariate setting using multiple output Gaussian processes. The paper engages closely with a case study focusing on the impact of the accelerated UK vaccination schedule, as contrasted with the rest of Europe, to illustrate the methodology and present the implementation procedure.