The First-Stage in an Instrumental Variable Approach to Controlling for Endogenous

Multiple Choice

The first-stage in an instrumental variable approach to controlling for endogenous independent variables is to

A) regress the endogenous independent variable on the instrument and all of the remaining independent variables and using those estimates to calculate predicted values of the endogenous variable.
B) regress the endogenous variable on the instrument and all of the remaining independent variables and using those estimates to calculate the residuals.
C) estimate the original population regression model with the predicted values of the endogenous variable substituted for the observed values of the endogenous variable.
D) estimate the original population regression model with the predicted residuals included as an independent variable.