Put up to three data sets next to each other: every summary statistic in one table and the shapes on a shared axis, so differences are obvious at a glance.
12 values
12 values
0 values
Box = middle 50% (Q1 to Q3), thick line = median, triangle = mean, dots = individual values.
| Statistic | Class A | Class B |
|---|---|---|
| n | 12 | 12 |
| Mean | 79.5833 | 71.6667 |
| Median | 79.5 | 71.5 |
| Standard deviation (s) | 9.1598 | 4.4381 |
| Min | 66 | 65 |
| Q1 | 71 | 68.5 |
| Q3 | 86.5 | 74.5 |
| Max | 95 | 80 |
| IQR | 15.5 | 6 |
| Coefficient of variation | 11.51% | 6.19% |
| Skewness | 0.087 | 0.288 |
| Outliers (1.5 × IQR) | none | none |
Difference in means: 7.9167; in medians: 8. To test whether this is more than sampling noise, run a two-sample t-test.
An AI tutor reads your numbers and explains what they mean in plain words. Sends only the inputs and results shown above.
Describe centre, spread, shape and unusual features, and use comparative words (“higher”, “more variable”) rather than listing each set separately. For example: “Class A’s median score (82.5) is higher than Class B’s (71.5), and A is more spread out (IQR 15.5 against 6.5); both are roughly symmetric with no outliers.”
For a single data set in depth, use the statistics calculator; for relative spread across scales, the coefficient of variation.
Compare centre (mean or median), spread (standard deviation or IQR), shape (symmetric or skewed) and unusual values (outliers). Always plot them on the same scale; numbers alone can hide differences that are obvious in a picture.
Use medians and IQRs if either data set is skewed or has outliers; use means and standard deviations if both are roughly symmetric. The table shows both so you can choose.
Descriptive statistics show how the samples differ, not whether that difference would hold in the wider population. For two groups of numbers, run a t-test (or a Mann–Whitney test for skewed data); for three or more groups, ANOVA. The t-test calculator on this site takes the same data.
Use the coefficient of variation (SD ÷ mean) to compare relative spread, or convert values to z-scores to compare positions within each set.