Explaining Data Simply
Introduction
Welcome to the fifth and final lesson of Comparing and Communicating Distributions! By now you have a powerful analytical toolkit at your fingertips: you can pair the right summary statistics with a distribution's shape, catch hidden structure that single summaries miss, describe an individual distribution thoroughly, and compare two distributions element by element using specific numerical evidence. That is a seriously impressive skill set.
This lesson brings everything together around one last and very practical question: who will read your comparison? In most professional settings, the person who needs your analysis is a manager, a client, or a teammate who has never taken a statistics course. If our well-structured comparison is packed with terms like "right-skewed," "IQR," or "standard deviation," the reader may nod politely and then set the report aside. Our goal today is to write comparisons that remain just as precise as before while being fully understandable to someone with no statistics background.
Why Your Audience Matters
Picture handing a report to a store manager that reads: "Location A's distribution is right-skewed with a median of minutes and an IQR of minutes, compared to Location B's roughly symmetric distribution with a median of minutes and an IQR of minutes." Every fact is correct and every number is there. But the manager's first thought might be, "What does IQR mean, and what should I do about this?"
The issue is not accuracy. It is accessibility. A comparison that a reader cannot understand is a comparison that will not influence any decision. Our task in this lesson is to keep all the precision we have practiced while removing the barriers that prevent non-experts from acting on the information.
Replacing Jargon with Plain Language
The first step toward accessible writing is recognizing which words count as jargon. Many terms that feel natural after a statistics course are unfamiliar to a general audience. The table below pairs common statistical terms with plain-language alternatives:
| Statistical term | Plain-language alternative |
|---|---|
| Median | Middle value, typical value |
| Mean | Average |
| IQR | Range of the middle 50% of values |
| Standard deviation | Typical distance from the average |
| Right-skewed | Pulled toward a few unusually high values |
| Symmetric | Roughly balanced above and below the center |
| Outlier | Unusually extreme value, far from the rest |
| Distribution | The pattern or spread of the values |
We do not need to remove numbers or water down the analysis. We simply need to translate each technical term into words the reader already knows. If a term is particularly useful, we can introduce it briefly in parentheses — for example: "the typical value (statisticians call this the median) was minutes." That way the reader picks up the vocabulary without needing it to follow the argument.
