5

I've been searching online for plots and analyses of the College Scorecard data, because I'm interested in analyzing the data myself. I don't want to reproduce what others have already done.

I've played around with the tools that the College Scorecard site provides, but they aren't exactly what I'm interested in... what I'm most interested in is producing a plot that clearly illustrates which colleges are most likely "scams" based on the data.

Can someone please point me to some interesting examples of some analyses/plots of the College Scorecard data? Thanks!

Improve this question
4
  • 2
    you won't find many references online, but one thing most people do not notice about the scorecard is that there are no scores. this is because schools didn't like their scores and complained to ed.gov. now that's an interesting story...
    – albert
    Feb 17, 2017 at 0:21
  • 1
    This analysis may be a good starting point: kaggle.com/benhamner/d/kaggle/college-scorecard/…
    – Scorecard_HelpDesk
    Feb 20, 2017 at 15:29
  • Ah thanks @Scorecard_HelpDesk, that's exactly the sort of analysis I was looking for. Thank you. And if you find more analyses of a similar kind please share!
    – Nic Scozzaro
    Feb 20, 2017 at 16:59
  • 2
    Maybe not what you're looking for, but I think this deserves a mention when someone's analyzing college scorecard data: hechingerreport.org/…
    – wirefire
    Feb 20, 2017 at 17:06

2 Answers 2

Reset to default
2

I've built an R-based app using the College Scorecard database. It uses the RStudio shinyapps.io server as the host.

Find it here: "Best Colleges For You" App .

Read the "About" section of the App to see its connection to the Kaggle.com College Scorecard script: "Which College is Best for You? Part_2".

Improve this answer
2

I ended up putting together an analysis of the College Scorecard data here: http://www.physicsisbeautiful.com/blog/collegescorecard-analysis/ in which I created a visualization of faculty salary vs tuition from 2001 to 2017, and I also used a random forest machine learning model to predict the colleges most likely to fail.

I also built a tool that enables interactively visualizing the CollegeScorecard data here: www.physicsisbeautiful.com/blog/collegescorecard/
You can hover over the data points to identify what I would consider as "scammy" colleges -- colleges that charge very high tuition but have very low faculty salaries. You can also dynamically change the axes to median debt upon entering repayment, median earnings of students 10 years after entry, or about 40 other interesting variables.

Improve this answer

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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