schooling	earnings
0	12.5572
1	12.37059
2	12.28345
3	12.53942
4	13.60204
5	13.69685
6	14.46392
7	15.48792
8	16.58223
9	17.75331
10	18.31583
11	18.93581
12	20.69255
13	22.40492
14	23.55711
15	25.12731
16	30.9133
17	30.25502
18	31.35148
19	31.24208
20	34.62525

The file "SchoolEarnings.csv" contains data on earnings and schooling.

The data is from a 1991 study by Angrist and Krueger entitled "Does Compulsory School Attendance Affect Schooling and Earnings?"published in the Quarterly Journal of Economics.

Angrist and Krueger obtained their data from the Integrated Public Use Microdata Series from the 1980 U.S. Census.

The study specifically focused on men born between 1930 and 1939, so they were 41-50 years old at the time of data collection.

Each row corresponds to a large group of men with the same level of schooling.

The variable "schooling" indicates the years of schooling for each group. 12 corresponds with high school completion, and 16 corresponds with college completion.

The variable "earnings" indicates the average annual earnings (in 1980 U.S. dollars) for the men in each group.

Now, run a linear regression (i.e. only using education as a predictor, not education squared) that only uses the data for men with 0-12 years of schooling. Report the coefficient on education. Does this coefficient look meaningfully different from the one you get when you include the full range of data?

Use this new regression to predict the income of someone with 16 years of education. Is this prediction accurate? Discuss: why do you think this prediction is (or is not) accurate?

Display keyboard shortcuts for Rich Content Editor