Diving into the NLSY97 dataset a bit right now and I thought I’d share some plots pertaining to IQ/achievement tests, income, GPA, educational attainment, and more. Nothing here is particularly novel, if you’ve looked for this sort of data before, but sometimes it’s nice to have additional independent analysis or alternative presentations of the data.
High school GPA-test score relationships
HS GPA by ASVAB in percentiles (IQ test)
HS GPA by PIAT (Peabody Individual Achievement Test, IQ test admin. in early childhood)
HS GPA by ACT composite score
[Note: Both the ACT and SAT suffer from some range restriction issues here relative to the ASVAB/AFQT, i.e., mostly the upper half of the ability distribution take it, not much below that]
IQ/test score relationships
PIAT by ASVAB
ASVAB by PIAT
SAT composite by ACT composite ACT composite by SAT composite ACT composite by ASVAB SAT composite by ASVAB ASVAB by SAT composite ASVAB by SAT verbal ASVAB by SAT mathSAT math by ASVAB
SAT verbal by ASVAB
2011 income / test score relationships
Income by ASVAB
Income by SAT math
Income by SAT composite
Income by ACT composite
IQ/test score by educational attainment level
The ASVAB is by far the best cognitive measure here since it is a decent test and it was administered to the vast majority of respondents (not true with the other tests here)! The reported SAT and ACT scores, for instance, suffer from both range restriction and self-selection issues, even though the tests are very well correlated with ASVAB. Nevertheless, I am including these other tests for completeness….
ACT composite score
Mean IQ by race, ethnicity, religion, etc
By Parents Education Levels
Note: I punched some quick numbers in for average years education as crude weights (S.W.A.G.) for cognitive intensity/discipline factor mainly, not as the necessarily actual empirical average number of years for each. None = 8, GED = 10, HS = 12,2-yr degree= 14,Bachelors = 16, Masters = 18, Professional degree = 20, PhD= 21 (the average PhD probably takes considerably longer than this now :-).