2019 Fiscal Year Final Research Report
Inference on causal effects for misclassified treatment
| Project/Area Number |
17K13715
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Economic statistics
|
|---|
| Research Institution | Kyoto University (2018-2019)
Hitotsubashi University (2017) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Keywords | 計量経済学 / ミクロ計量経済学 / 政策評価 / 測定誤差 |
|---|
| Outline of Final Research Achievements |
In this study, I examined statistical causal inference models in which the causal variable may be misclassified due to the presence of measurement error. I obtained the following results. First, I clarified identification problems caused by the presence of measurement error. Then, I proposed new identification results for local average treatment effects, which is one of the most important causal parameters in the literature, when the causal variable may be misclassified. Based on the identification result, I also proposed estimation procedures for the local average treatment effects. In addition, I studied how to extend these results to other statistical causal inference models.
|
| Free Research Field |
計量経済学
|
| Academic Significance and Societal Importance of the Research Achievements |
政策の効果を評価するために，経済学の実証研究では局所平均処置効果モデルを利用することが多い．経済学の実証研究ではデータ収集の過程で原因変数にエラーが含まれてる可能性があるが，これまでの多くの実証研究ではそのようなエラーから生じる問題に対処できていなかった．本研究で得られた研究成果を利用すれば，このようなエラーから生じる問題を解決できるとともに，政策の効果を正しく評価できる蓋然性を高めることができるといえる．
|
