00:01
A, the wage equation may not be estimated satisfactorily using the least square estimators due to potential endogeneity problem.
00:24
Endogeneity arises when an explanatory variable in the model is correlated with the error term.
00:29
In this case, the number of hours worked is likely to be endogenous because it is determined by both wage rate and number of young children in the household.
00:56
If we ignore this endogeneity and estimate the wage equation using ordinary least squares, our estimates will be biased and inconsistent.
01:06
B, the wage equation is not identified if we only have data on wages, hours worked, education and experience.
01:19
Identification in this context means that we can uniquely estimate the parameters of wage equation.
01:25
For identification, we need at least as many exogenous variables as endogenous variables.
01:38
In this case, we have one endogenous variable that is hours and three exogenous variables which is education, experience and constant term.
02:04
However, we also need an instrument for hours that is correlated with hours but uncorrelated with error term in the wage equation...