Recent Grads' Cumulative Student Loan Debt

​Scott Baumler
Director of Institutional Research
Loras College

Averages tell the truth – but only on average. To describe more of the story, consider using a box plot.

A box plot diagrams the quartiles of a dataset, as shown here. In addition, this visual conveys a sense of the raw data distribution by showing the actual data points behind the boxes.

Student loan debt is often reported using averages. The mean alone, however, does not convey information about the spread of observations. This visual is meant to help impart an understanding of the range of experience. Further, it demonstrates how the average can be “pulled up” by large values (as compared to the median).

The tables that accompany the box plot may be a bit redundant but were included to help uninitiated readers connect the dots. The text plainly lists counts, sums, averages, and medians to demonstrate how the figures are calculated (i.e., number of graduates compared to those with debt), prompt consideration of how point estimates relate to the entirety of the dataset, and illustrate how outliers can affect measures of central tendency.

The interquartile range (middle 50%) values could be listed in a table for ease of reference and citation. Per capita figures could also be calculated from the tabular information to further demonstrate different analytical vantage points.

 View larger version of box plot image (PDF opens in new tab). 


Cumulative student loan debt of recent graduates

Includes undergraduate students who started as first-time students and received bachelor's degrees. "Grad year" runs from July 1 of the preceding year to June 30 of the named grad year. Excludes students who transferred in; money borrowed at other schools; parent loans; and students who did not graduate. Shows only undergraduate borrowing. Figures not adjusted for inflation.

Sample data for illustrative purposes only

Each blue dot represents an individual student. Denser areas (darker colors) indicate where more students are located. The top of each box represents the 75th percentile; the line where the box color changes from orange to purple is the median; the lower edge of the box is the 25th percentile. The red, dashed horizontal line shows the average. The "whiskers" represent the range of the data.



To add a comment, Sign In
Total Comments: 1
Scott posted on 11/10/2016 1:43 PM
To reiterate, these are sample data for illustrative purposes only.