JUDGING INSTRUMENT RELEVANCE IN INSTRUMENTAL VARIABLES ESTIMATION

Recent research has emphasized the poor finite-sample performance of t he instrumental variables (IV) estimator when the instruments are weak ly correlated with the regressors. We show how the canonical correlati ons between regressors and instruments can provide a measure of instru ment relevance in the general multiple-instrument-multiple-regressor c ase. However, our simulation results indicate that any such relevance measure probably has little practical merit, as its use may actually e xacerbate the poor finite-sample properties of the IV estimator.