Online Program Home
My Program

Abstract Details

Activity Number: 47 - Highlights from Bayesian Analysis
Type: Invited
Date/Time: Sunday, July 28, 2019 : 4:00 PM to 5:50 PM
Sponsor: Section on Bayesian Statistical Science
Abstract #300005 Presentation
Title: Bayesian Method for Causal Inference in Spatially Correlated Multivariate Time Series
Author(s): Bo Ning*
Companies: Yale University
Keywords: advertising campaign; Bayesian variable selection; causal inference; graphical model; stationarity; time series

Measuring the causal impact of an advertising campaign on sales is an essential task for advertising companies. Challenges arise when companies run advertising campaigns in multiple stores which are spatially correlated, and when the sales data have a low signal-to-noise ratio which makes the advertising effects hard to detect. This paper proposes a novel Bayesian method to detect weaker impacts by comparing two posterior distributions of a latent variable—one obtained by using the observed data from the test stores and the other one obtained by using the data from their potential outcomes. A multivariate structural time series model is used to conduct the analysis. We capture the spatial correlation between stores through placing a G-Wishart prior on the precision matrix. Control stores are selected using an Expectation-Maximization variable selection method. To prevent the prediction intervals from being explosive, a stationarity constraint is imposed on the local linear trend of the model through a recently proposed prior. A detailed simulation study shows the effectiveness of using our proposed method to detect weaker causal impact. The new method is applied to a real dataset.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program