报  告  人：于雪雯（London School of Economics and Political Science）

报告时间：12月13日（周五）15：00-17：00

报告地点：数学楼（海纳苑2幢 ）203室

报告摘要: The Bayesian Structural Times Series (BSTS) model has been adopted to evaluate the causal effects of policy implementations. The framework integrates the synthetic controls method to forecast the counterfactual time series and employs a spike-and-slab prior for variable selection, which requires users to specify the expected number of variables to include. However, eliciting this number from prior knowledge is usually hard. Moreover, the model can only be applied to a single treated unit. To address these limitations, we propose a hierarchical BSTS. This framework is flexible to account for individual-level variance and is more robust to misspecification of the expected number of variables. We apply this model to evaluate the impact of the Immigration Act established by the UK government in 2014 on the mental wellbeing of ethnic minorities.

报告人简介：Xuewen’s research interest lies in causal inference methods, bayesian inference, and their applications in population health. Xuewen’s worked on chain event graphs during her PhD and developed a hierarchical model to improve predictions of machine’s failure by incorporating the bespoke causal algebras. Before joining LSE, Xuewen worked on continuous-time g-methods to assess the effect of time-varying treatment when the treatment decision changes sporadically throughout the follow-up period. Her current work focuses on quasi-experimental design and policy evaluation.