vii. Add the two college tuition variables to the regression from part (iv) and determine whether they are jointly statistically significant.

A:

viii. What is the correlation between tuit17 and tuit18? Explain why using the average of the tuition over the two years might be preferred to adding each separately. What happens when you do use the average?

A:

ix. Do the findings for the average tuition variation in part (vii) make sense when interpreted causally? What might be going on?

regress educ motheduc fatheduc abil tuit17 tuit18 Source SS df MS Number of obs = 1, 230 F (5, 1224) 183 . 42 Model 2917 . 90706 5 583. 581411 Prob > F E 0 . 0000 Residual 3894. 37262 1, 224 3. 18167698 R-squared E 0 . 4283 Adj R-squared 0 . 4260 Total 6812. 27967 1, 229 5. 54294522 Root MSE 1. 7837 educ Coefficient Std. err. t P> [ t| [95% conf. interval] motheduc . 1919613 . 0285912 6. 71 0 . 000 . 135868 . 2480546 fatheduc . 1107391 . 0199006 5. 56 0 . 000 . 071696 . 1497822 abil . 4997098 . 0258092 19 .36 0 . 000 . 4490746 . 550345 tuit17 . 0319452 . 0633576 0 . 50 0 . 614 0923562 . 1562467 tuit18 0164251 . 064518 -0 . 25 0 . 799 -. 1430032 . 110153 cons 8 . 290854 . 3154119 26. 29 0 . 000 7 . 672046 8 . 909662