Collaborative Research: Transparency and Misspecification in Structural Estimation

许多经济研究试图将经济理论和统计模型结合起来，从数据中得出与政策相关的结论。这一过程的透明度——目标受众是否能够理解结论背后的证据以及结论本身——对政策相关研究的成功至关重要。本项目将开发一个框架，用于理解取得成果的过程，以及向不同受众传播科学发现，将该框架应用于应用经济学中的重要问题，并研究经济学家如何从数据中得出更稳定的与政策相关的结论，这些结论不会因数据或方法的微小变化而发生变化。该研究有三个项目：科学传播研究，透明度的定义和测量，以及如何在经济学研究中实现透明度的项目。本文的研究结果将有助于开展更有效、更可靠的政策相关经济学研究。这也会增加人们对经济政策研究的信任，从而制定出更好的政策。该项目将研究科学研究的透明度。本研究包括三个项目：第一个项目将运用经济理论和统计决策理论提出并发展一个科学传播模型，并将其与经典统计模型的含义进行对比。第二个项目——结构评估中的透明度——为结构评估提供了透明度的工作定义，并讨论了实现它的方法。第三个项目题为“结构模型中对错误说明的工具选择和敏感性”，将发展和说明工具选择在确定结构模型对错误说明的估计敏感性方面的重要性。本项目的研究成果不仅对计量经济学理论和实践有一定的贡献，而且对政策和项目评估的改进也有一定的参考价值。这项研究改善了经济和政策决策，从而加强了美国经济。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Much economic research seeks to combine economic theory and statistical modeling to derivepolicy-relevant conclusions from data. The transparency of this process—whether the intendedaudience can understand the evidence behind the conclusions as well as the conclusionsthemselves—is crucial to the success of policy relevant research. This project will develop a framework for understanding the process through which the results were achieved, as well as the communication of scientific findings to a diverse audience, apply the framework to important problems in applied economics, and study how economists can reach more stable policy-relevant conclusions from data that does not change with minor changes in data or methodology. The research has three projects: a study of scientific communication, a definition and measurement of transparency, and a project that focuses on how to achieve transparency in economics research. The results of this research will lead to more efficient and reliable policy relevant economics research. It also will result in more trust in economic policy research as well as the development better policies.The project will study transparency in scientific research. The research consists of three projects: The first project will use economic theory and statistical decision theory to propose and develop a model of scientific communication and contrast its implications with those of a classical model of statistics. The second project---Transparency in Structural Estimation---provides a working definition of transparency for structural estimation and discusses approaches to achieving it. The third project titled “Instrument Selection and Sensitivity to Misspecification in Structural Models” will develop and illustrate the importance of instrument choice in determining the sensitivity of estimates of structural models to misspecification. The results of this research project does not only contribute to econometric theory and practice but also to improvement of policy and program evaluation. This research improves economic and policy decision making, hence strengthens the US economy.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.