动态空间贝叶斯机器学习模型：美国代际经济流动性与地理收入不平等中的应用
Dynamic Spatial Bayesian Machine Learning Model: Applications to Intergenerational Economic Mobility and Geographic Income Inequality in the United States
浏览论文内容
中文总结 AI 辅助
本文提出带Horseshoe收缩的动态空间面板贝叶斯加性回归树模型（DSP-BART-HS），用于高维时空数据，在九个场景中表现最优或相当，并在美国县级代际流动与收入不平等应用中验证了预测性能与变量选择。
中文摘要 AI 辅助
我们开发了一种带有Horseshoe收缩的动态空间面板贝叶斯加性回归树模型（DSP-BART-HS），用于高维时空面板数据。我们在一套全面的结构空间计量经济学、非参数机器学习方法和小区域估计器中，联合评估了该模型，涵盖九个数据生成场景，每个场景包含200次重复，包括不规则空间拓扑、密集政策效应和非线性个体层面交互。DSP-BART-HS在每个场景中都是最佳或与最佳估计器在统计上无显著差异。传统的区域-时间聚合比较器在个体层面非线性驱动结果方差时，性能严重下降——落后三倍或更多——而该框架的树集成设计直接解决了这一局限。该模型还通过其空间扩散机制，在零训练区域空间留出法下保持了强大的预测准确性。我们在两个美国县级面板应用中展示了实际效用——代际经济流动性和地理收入不平等——在真正的未见区域、随机和时间留出法下，并通过重复分割不确定性量化和与每个比较器的配对显著性检验验证了结果。一个明显的局限出现了：在时间外推下，一种更轻的每区域自回归规格（MTS-CAR-X）实现了稳健且一致的优越性。尽管如此，DSP-BART-HS为分层时空面板数据建立了强大的预测性能、自动变量选择和灵活推断。
英文摘要
We develop a Dynamic Spatial Panel Bayesian Additive Regression Trees model with Horseshoe shrinkage (DSP-BART-HS) for high-dimensional spatio-temporal panel data. We jointly evaluate the model against a comprehensive suite of structural spatial econometrics, non-parametric machine learning methods, and small-area estimators across nine data-generating scenarios spanning 200 replicates each, including irregular spatial topologies, dense policy effects, and non-linear individual-level interactions. DSP-BART-HS is the best or statistically indistinguishable from the best estimator in every scenario. Conventional region-time-aggregate comparators suffer severe performance degradation -- trailing by a factor of three or more -- whenever individual-level non-linearity drives outcome variance, a limitation this framework's tree-ensemble design directly addresses. The model also maintains strong predictive accuracy under a zero-training-region spatial holdout via its spatial diffusion mechanism. We demonstrate practical utility across two U.S. county-level panel applications -- intergenerational economic mobility and geographic income inequality -- under genuine unseen-region, random, and temporal holdouts, with results validated through repeated-split uncertainty quantification and paired significance testing against every comparator. One clear limitation emerges: under temporal extrapolation specifically, a lighter per-region autoregressive specification (MTS-CAR-X) achieves a robust, and consistent advantage. DSP-BART-HS nonetheless establishes strong predictive performance, automated variable selection, and flexible inference for hierarchical spatio-temporal panel data.
