发帖
雷达卡
摘要翻译：
我们分析了不同的评估基于模拟，应用研究人员可以用来评估他们的推断方法的可靠性。我们表明，不同类型的模拟在许多维度上是不同的，当考虑到推理评估时，会出现微妙的问题。我们提供的证据表明，即使使用简单和易于实施的评估，也可以在许多不同的环境中发现问题。虽然更复杂的评估可能会发现更简单的评估无法发现的问题，但在这一维度上，它们并不统一地主导更简单的评估。此外，考虑更复杂的评估可能会产生一些成本，从应用程序特定修改的必要性到顺序测试的扭曲。
---
英文标题：
《Assessing Inference Methods》
---
作者：
Bruno Ferman
---
最新提交年份：
2021
---
分类信息：
一级分类：Economics 经济学
二级分类：Econometrics 计量经济学
分类描述：Econometric Theory, Micro-Econometrics, Macro-Econometrics, Empirical Content of Economic Relations discovered via New Methods, Methodological Aspects of the Application of Statistical Inference to Economic Data.
计量经济学理论，微观计量经济学，宏观计量经济学，通过新方法发现的经济关系的实证内容，统计推论应用于经济数据的方法论方面。
--
---
英文摘要：
We analyze different assessments based on simulations that applied researchers may use to evaluate the reliability of their inference methods. We show that different types of simulations vary in many dimensions and present subtle issues when considered as inference assessments. We present evidence that even the use of simple and easy-to-implement assessments can detect problems in many different settings. While more complex assessments may detect problems that simpler assessments would not detect, they do not uniformly dominate simpler assessments in this dimension. Moreover, considering more complex assessments may induce some costs, ranging from necessity of application-specific modifications to sequential-testing distortions.
---
PDF链接：
https://arxiv.org/pdf/1912.08772
京公网安备 11010802022788号
