Bayesian Indicator-Saturated Regression for Climate Policy Evaluation

2026-03-05

AI Summary

This study addresses the challenge of unknown number and locations of structural breaks in climate policy evaluation by proposing a unified Bayesian probabilistic framework. By integrating a spike-and-slab prior with an inverse-moment-density slab component and a saturated regression model with indicator variables, the method enables accurate identification of an arbitrary number and positions of structural breaks in longitudinal data. The approach is theoretically guaranteed to achieve model selection consistency and demonstrates marked superiority over existing frequentist methods, particularly under high break probabilities. Empirical application to European road transport sector data illustrates its practical utility and innovation in causal inference for climate policy impact assessment.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Planning, Routing, and Scheduling: Planning under Uncertainty

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Structural break identification methods are an important tool for evaluating the effectiveness of climate change mitigation policies. In this paper, we introduce a unified probabilistic framework for detecting structural breaks with unknown timing and arbitrary sequence in longitudinal data. The proposed Bayesian setup uses indicator-saturated regression and a spike-and-slab prior with an inverse-moment density as the slab component to ensure model selection consistency. Simulation results show that the method outperforms comparable frequentist approaches, particularly in environments with a high probability of structural breaks. We apply the framework to identify and evaluate the effects of climate policies in the European road transport sector.

Problem

• structural break
• climate policy evaluation
• longitudinal data
• Bayesian inference
• indicator-saturated regression

Innovation

• Bayesian indicator-saturated regression
• structural break detection
• spike-and-slab prior
• inverse-moment density
• climate policy evaluation