Question

1. Labor economists often study the returns on investment in education (see, e.g. Card 1999). Suppose we have data on salaries of a set of people, some of whom went to college and some who did not. A simple model linking education to salary is, Salaryi = Bo + Bi College graduate; + Eig where the value of Salary: is the salary of person i and the value of College graduate; is 1 if person i graduated from college and 0 if person i did not a. What does Bo mean? what does B, mean? b. What variables do you believe are in the error term? c. What are the conditions for the independent variable College graduate; to be endoge- nous? Do you believe the independent variable College graduate; is endogenous? Why or why not? d. Explain how endogeneity could lead to incorrect inference about how getting higher education affects future earnings.

Answer 1

a. $\beta o$ depicts the salary of person when the level of college graduation of equal to zero. Thus, it is the intercept term depicting salary of a non-college graduate. $\beta 1$ depicts the change in the salary of the person when the person is a college graduate.

b. Salary of the person is also determined by skill set of the person,work experience level of the person, efficiency level of the person etc. These variables are included in the error term.

c. Independent variable is endogenous if it is determined within the model using simultaneous equation model. No, the independent variable is not endogenous rather it is exogenous and determined outside the model and also has no correlation with the error term. This is needed as an assumption of Ordinary least Square Model.

d. It can lead to underestimation of the inference of how getting higher education affects future earnings.