Research

Home -> Research -> Publications -> Content

Research

The Validity of Instruments Revisited

Id：2149 Date：20131014 Status：published ClickTimes：
作者Daniel Berkowitz, Mehmet Caner, Ying Fang
正文This paper shows how valid inferences can be made when an instrumental variable does not perfectly satisfy the orthogonality condition. When there is a mild violation of the orthogonality condition, the Anderson-Rubin (1949) is oversized. In order to correct this problem, the fractionally resampled Anderson-Rubin test is derived by modifying Wu’s (1990) resampling technique. We select half of the sample when resampling and obtain valid but conservative critical values. Simulations show that our technique performs well even with moderate to large violation of exogeneity when there is a finite sample correction for the block size choice.
JEL-Codes：C3, C13, C30.
关键词：Berry-Esseen Bound, Finite Sample of Random Variables, Near-Exogeneity
TOP