In the College Scorecard data set there are three variables that define a working_not_enrolled earnings:

[1] earnings.6_yrs_after_entry.mean_earnings.dependent_students (Mean earnings of dependent students working and not enrolled 6 years after entry) [2] earnings.6_yrs_after_entry.mean_earnings.independent_students (Mean earnings of independent students working and not enrolled 6 years after entry)


[3] earnings.6_yrs_after_entry.working_not_enrolled.mean_earnings (Mean earnings of students working and not enrolled 6 years after entry)

I was thinking to combine both dependent[1] and independent[2] student data to get the overall mean earnings of all students which I thought would be the same as the last variable[3], but it isn't.

So which is the "true" mean earnings for all students here?


I have spoken with someone familiar with the data. He compared the mean earnings overall to a recalculated version from the independent and dependent student subpopulations and found that the differences were within an acceptable rounding tolerance. If you believe this not to be the case, can you provide us with some examples that illustrate the issue?

He also suggested the best overall average is your item [3] above, as it is built directly from the underlying data and not rounded subpopulation figures.

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Not the answer you're looking for? Browse other questions tagged or ask your own question.