2. (20 pts} Suppose we observe {edug,D};\"=1 where edug denotes an individual's years of education, 19- _ { 1 if at least one parent has a college degree 0 if neither parent has a college degree We estimate a linear regression edu = 61 + QD | e and obtain the following results bl _ 10.5 @(a) _ 3.8 b2 _ 4.3 rm) _ 1 (a) What is the estimate of the expected number of years of education for an individual who had at least one parent attend college? (b) Suppose D\" 2 2321 D1; / n. = 0.56. What is the average of edu in this sample? (c) Build a 90% condence region for g employing a normal approximation. {(1) Can you build a 95% condence region for g employing a tapproximation? If yes, then report what it is. If not, then explain why not. (e) The regression estimates imply individual's whose parents went to college are more likely to be more educated. However, they do not imply they are more education because their parents went to college. Suppose parental income is positively correlated with whether they attended college. How could that explain our estimates