Working Paper: NBER ID: w27797
Authors: Steven J. Haider; Melvin Stephens Jr.
Abstract: Estimators that exploit an instrumental variable to correct for misclassification in a binary regressor typically assume that the misclassification rates are invariant across all values of the instrument. We show that this assumption is invalid in routine empirical settings. We derive a new estimator that is consistent when misclassification rates vary across values of the instrumental variable. In cases where identification is weak, our moments can be combined with bounds to provide a confidence set for the parameter of interest.
Keywords: misclassification; instrumental variables; binary regressors
JEL Codes: C18; C26
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| misclassification rates vary with the instrumental variable (C36) | existing estimators for correcting misclassification in binary regressors are inconsistent (C20) |
| proximity to eligibility thresholds (I24) | misclassification rates (C52) |
| varying misclassification rates (C52) | overestimation or underestimation of the true parameter of interest (C51) |
| new estimator (C51) | consistent estimates of the impact of misclassified binary regressor (C20) |