Instrumental Variable Estimation in a Data Rich Envirornment

Joint with: Jushan Bai

We consider estimation of parameters in a regression model with endogenous regressors. The endogenous regressors along with a large number of other endogenous variables are driven by a small number of unobservable exogenous common factors.

We show that the estimated common factors can be used as instrumental variables. These are not only valid instruments, they are more efficient than the observed variables in our framework. Consistency and asymptotic normality of the single equation factor instrumental variable estimator (FIV) is established. We also consider estimating panel data models in which all regressors are endogenous. We show that valid instruments can be constructed from the endogenous regressors which are themselves invalid instruments.

For more information, contact Frank Schorfheide.