Data Analysis on the Effect of College Selection on ROI

Posted on Feb 3, 2020
The skills the author demoed here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.

LinkedIn | GitHub | ResearchGate


Data shows college selection is an exciting, yet anxiety-inducing, process for high school seniors and parents alike. While higher education was seen as a period for self-exploration and expanding one's mind, ever-increasing tuition costs have forced a sense of pragmatism - emphasizing university as an investment. Growing up in Texas, I attended Texas Tech University as most students apply to public universities due to the strength of the state institutions. Moving to Philadelphia to attend Drexel University and the University of Pennsylvania exposed me to emphasis placed on private and Ivy League education in the North-East corridor.

This experience begs the question: What is the expected return on investment of higher education? Is there a difference between public and private universities, and is this different regional? What majors yield the highest return? 

Using a dataset obtained from a website using a custom-written Selenium web scraper, the current project aims to explore the relationships between levels of education, type of education, major, and region, and estimated 20 year ROI. The results of the present study found that the benefits of a private school education may be limited to the North East, and noted differences between public and private school ROI when broke down by major. This information may be vital as students and families plan for the future. 

A picture I took on my rainy walk back from the the Van Pelt library on Penn's campus


Python and the Selenium library were used to web scrape, a public-facing research center that collects education and salary data collected from 3.5 million civilian employees. Three specific sites were scraped to collect (1) early- and mid-career salaries of bachelor and associate degrees; (2)  estimated ROI per college, by state; and (3) estimated ROI by major. 

Cumulative data scraped included state, college name, college type (private and public universities), early- and mid-career salary (median 0-5yr and 5-10yr, respectively), estimated 20yr ROI variables, and ROI of universities with and without financial aid. Researchers at PayScale estimated 20yr ROI by factoring in 20yrs of median salary earned by bachelor-only graduates, 24yr average high school salary, and cost of university.

Additionally, data obtained from service academies (ie. military academies) and data including out-of-state metrics from Public universities were excluded from analyses as they would have minimized differences between Public and Private education metrics.

Data Results

Earn more with a bachelor's degree

Comparisons of early- and mid-career salaries of post-graduates with a four-year Bachelor's and two-year Associate's degrees are featured in Figure 1. Within the first five years following graduation, mean salaries were $42.9k and $41.4k for Bachelor's and Associate's degrees, respectively.  However, differences in mid-career salaries between bachelor's and Associate's degrees widened, increasing to $88.7k and $61.2k, respectively. 

Data Analysis on the Effect of College Selection on ROIFigure 1. Early and mid-career salary by four-year Bachelors's degree and two-year Associate's degree. 

Data on Financial Aid props up the ROI of private universities

A histogram of estimated 20yr ROI of public and private universities, with and without financial aid is found in Figure 2. Key differences between ROI distribution should be noted. Without financial aid, bachelor-only graduates from 11.3% of private schools and 2.0% of public schools, can expect a negative return of investment. However, with the addition of financial aid, bachelor-only graduates from 4.7% of private schools and 0.6% of public schools resulted in an estimated loss of investment after 20 years. 

Data Analysis on the Effect of College Selection on ROI
Figure 2. Count distribution of estimated 20yr ROI of Bachelor graduates. Out-of-state ROI and military service academies were excluded from analysis. 

A private education may not be beneficial in each state

The percent difference between the estimated 20yr ROI of private and public universities, per state, are featured in Figure 3. Percent difference was calculated as [avg. Private ROI - avg. Public ROI)/(avg. ROI)*100]. States with negative percent different means that on average, ROI from public universities was greater than private universities, per state.

A noticeable trend was observed that private schools resulted in a higher 20yr ROI primarily in the northeast. Independent T-tests were performed to identify significant differences between ROI of Private and Public universities, per state (p < 0.05). Results from the statistical analyses found that public universities in AL, CA, KY, MI, OH, SC, TX, and VA resulted in a significantly higher return of investment than private universities (p < 0.05); only in PA did attending a private university result in a significantly higher ROI than public universities (p < 0.05). 

Data Analysis on the Effect of College Selection on ROI
Figure 3. Percent difference in 20yr ROI between Private and In-State Public colleges. %diff > 0% indicates Private ROI > Public ROI. [Equation: (Private-Public)/(avg ROI)*100]

Data on Differences in ROI existed between college majors

Boxplots of estimated 20yr ROI by college major are featured in Figure 4. An Independent one-way ANOVA with Tukey's post hoc analysis was performed to discern significant differences in estimated ROI between majors. Significant differences were observed (p < 0.05), computer science, economics, and engineering majors. Shamefully, Education majors resulted in the lowest estimated 20yr return on investment.

Data Analysis on the Effect of College Selection on ROI

Figure 4. ROI by college major groupings.

Data on Differences in ROI between private and public education dependent on major

Boxplots of estimated 20yr ROI by college major, per Private and Public universities, are featured in Figure 5. Independent T-tests were performed to identify significant differences between ROI of Private and Public universities, per major. Significant differences between estimated ROI between private and public schools exist per major, however no significant difference were observed for art, nursing, political science, and social work/criminal justice (p<0.05).

Figure 5. ROI of Private and Public universities, by college major groupings.


The results of the current project should be considered when selecting a college and major. Graduates of four-year colleges significantly out-earned their associate degree counterparts, earning 17% more within 0-5yrs; increasing to 36% in year 5-10. Available data did not allow for 20yr ROI comparisons that would account for differences in education cost. Financial aid/grants subsidized as much as 11% of four-year private colleges that would otherwise result in a negative ROI. Only 2% of four-year public universities returned a negative ROI without financial aid. 

Attending a higher-priced four-year private university may only be financially beneficial in the north-east corridor. Public universities in AL, CA, KY, MI, OH, SC, TX, VA significantly improved estimated ROI compared to private schools. Significant differences between estimated ROI exist between college majors, with computer science, economics, and engineering majors had the highest estimated ROI. Differences between estimated ROI between private and public schools exist per major, however, no significant difference were observed for art, nursing, political science, and social work/criminal justice.


Although this project successfully presented analyses that may potentially aid the college decision-making process, a significant flaw in the estimation of 20yr ROI minimizes the validity of the reported results.  Estimated ROI takes into consideration (1) 20yr median pay for bachelor-only grads, (2) 24yr median pay for high school grad, and (3) total four-year cost of the university. The estimation incorrectly assumes the cost of the university is the list price and doesn't take into consideration loan interest and length of repayment.

A recent government report found that the typical repayment period for borrows with between $20k and $40k in student loans was over 20 years []. For example, a student with $100k in federal loans, with an 8% interest compounded monthly, the actual cost of higher education would be over $200k - generously assuming a 20yr repayment period. Including interest and repayment period would dramatically change the ROI of colleges across the country, and the analyses presented.

About the Author

If you would like to learn more about the author, please check out my LinkedIn profile. Furthermore, if you would check out my relevant code, please check out my GitHub account. 

About Author

Jon Harris

Jon is a certified Data Scientist and accomplished quantitative healthcare researcher with real-world experience in research methodologies, interpreting experimental results data, statistical and machine learning modeling, and creating data-driven narratives for multi-level stakeholders. Looking to utilize my strong...
View all posts by Jon Harris >

Related Articles

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI