arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.13355econ.EMstat.APstat.ME
收藏

考虑无知的证据聚合:学习已知与未知以发现原型

Evidence aggregation with ignorance in mind: learning what we do (not) know for archetypes discovery

Emily Breza, Arun G. Chandrasekhar, Davide Viviano

AI总结:

提出一个框架,在聚合处理效应异质性时,识别并排除不可靠外推的环境,同时学习如何总结异质性效应并承认无知,提供有限样本后悔保证和推断程序。

摘要:

在评估政策干预时,研究者通常追求两个相关目标:识别哪些个体或情境受益最大,以及确定处理效应异质性的模式是否可用于跨环境聚合证据。我们开发了一个框架,将定义在个体和环境特征上的处理效应异质性聚合为可解释的总结,同时排除外推不可靠且需要进一步证据的环境。因此,该过程既学习如何总结异质性效应,也学习研究者何时应承认无知。我们推导了有限样本后悔保证,提供了选择总结类复杂性的数据驱动保证,以及量化后续数据收集价值的推断程序。我们通过重新分析在六个国家实施的多方面反贫困项目来展示该方法。

英文摘要:

When evaluating policy interventions, researchers often pursue two related goals: identifying which individuals or contexts benefit most, and determining whether patterns of treatment effect heterogeneity can be used to aggregate evidence across environments. We develop a framework that aggregates treatment effect heterogeneity, defined over individual and environmental characteristics, into interpretable summaries while setting aside contexts in which extrapolation is unreliable and further evidence is needed. The procedure therefore learns both how to summarize heterogeneous effects and when researchers should admit ignorance. We derive finite-sample regret guarantees, provide data-driven guarantees for selecting the complexity of the summary class, and inference procedures that quantify the value of follow-up data collection. We illustrate the approach by reanalyzing a multifaceted anti-poverty program implemented in six countries.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑