This is through the estimation results. You have points as a function of experience. Experience. Square age and college are simple. Has almost 270 observations. And our square of this regression is 0.1 for one. So here I have their estimated coefficient written in blue and their standard errors in green in the bracket. In part two, you will define a turn around point of experience. You will find the partial derivative of points. Wow, with respect, Thio experience. Yeah, and you will get the coefficient of experience 2.364 miners to times the coefficient of Experience Square, which is 0.7 37. The turning point of experience is the level of experience that makes this partial derivative equal to zero. So you in set, uh, forgot times experience here. You will set this equation. Yeah, equals zero, and you can find the value of turning point experience that is 2.364 divided by two times 0.77 and you wouldn't get roughly 15.4. So the increase from 15 to 16 years of experience would actually reduce salary. This is a very high level of experience, and we can essentially ignore this prediction. Only two players in the sample of 269 have more than 15 years of experience in the next part, part three. You may see that college has a negative and statistically significant coefficient. And based on the hint of the problem written in the problem, okay, you may know that many of the most promising players leave college early or, in some cases, forgo college altogether to play in the n. B. A. These top players command the highest salaries. It is not more college that hurts salary, but less college is indicated of superstar potential. In Part four, you will add Age Square to the regression from Part one. It's coefficient is is it 10536 with a standard error of 0.492 It's T statistic. It's very above one, and recall that he start is the ratio of beta hat over the standard error of beta hat. You have 0.5 divided by 0.4 That is slightly above one so we can drop this variable. It is not significant in the same regression, the coefficient on age is minus 3.984 with a standard error of 2.6 89 Together, these estimates imply a negative increasing return to age. The turning point is roughly at 74 74 years old. And again you find that turning point by finding the value of age that makes these partial derivative of points. We respect you. Age equals zero in any case, the linear function of age since sufficient Part five This is the L s results where you regret lock of which on points experience, age and the quadratic of experience and age intercept is 6.78 coefficient of points is 0.78 of experience coefficient is 0.218 For Experience Square, it is minus 0.71 for H is 0.48 And for college. Oh, I should say there is no quadratic form of Asia. We consider we conclude we should drop it from part four. So the last variable is college. We have 0.4 as it's coefficient. The our square is point 49 Let me filled out their standard error really quick. We have 0.85 for the intercept point. 0074 points 0.5 for Experience 0.28 for Experience Square, 0.35 for age and 0.53 for college now last part part six in part six you in test whether age and college are jointly significant in the regression from Part five. Yeah, the non hypotheses is beta of the two variables, age and college both equals zero you will get you will do an F test. The F statistic you get with two and 263 degrees of freedom is about 1.19 and the P value associate it with this F test is roughly 0.31 So we are unable to reject the null hypotheses. Age and college are statistically insignificant. This means on scoring and years played are controlled, for there is no evidence for which differentials, depending on age or years, played in college.