A cautionary note on tests for overidentifying restrictions
Tests of overidentifying restrictions are widely used in practice. However, there is often confusion about the nature of their null hypothesis and about the interpretation of their outcome. In this note we argue that these tests give little information on whether the instruments are correlated with the errors of the underlaying economic model and on whether they identify parameters of interest.
Year of publication: |
2011-11-11
|
---|---|
Authors: | Parente, Paulo M.D.C. ; Silva, J.M.C. Santos |
Saved in:
freely available
Saved in favorites
Similar items by person
-
Quantile regression with clustered data
Silva, J.M.C. Santos, (2013)
-
Quantile Regression with Clustered Data
Parente, Paulo M.D.C., (2016)
-
Quantile regression with clustered data
Parente, Paulo M.D.C., (2013)
- More ...