**The most counterintuitive finding is that setosa has the widest sepals of the three species, even though it is the smallest flower on every other measure.** I'm reading this from the `Iris_by_Species` gold table. | Measure (species average) | Setosa | Versicolor | Virginica | |---|---|---|---| | Sepal length (cm) | 5.01 | 5.94 | 6.59 | | Petal length (cm) | 1.46 | 4.26 | 5.55 | | Petal width (cm) | 0.24 | 1.33 | 2.03 | | **Sepal width (cm)** | **3.42** | **2.77** | **2.97** | - **Size ordering breaks on sepal width.** Sepal length, petal length and petal width all rise from setosa to versicolor to virginica. Sepal width does not: setosa is widest at 3.42 cm, virginica is next at 2.97 cm, and versicolor is narrowest at 2.77 cm. - **A "bigger flower means bigger everything" assumption would therefore mislead.** Setosa's sepals are short but wide, so they are proportionally much rounder than the other two species'. - **Setosa is cleanly separable on petals, but the other two are not.** - Setosa's largest petal length is 1.9 cm, and versicolor's smallest is 3.0 cm. Its largest petal width is 0.6 cm, against versicolor's smallest at 1.0 cm. A single threshold on either petal measure isolates setosa completely. - Versicolor and virginica overlap on petal length (4.5–5.1 cm) and petal width (1.4–1.8 cm). - Their sepal lengths overlap across almost the whole versicolor range (versicolor 4.9–7.0 cm, virginica 4.9–7.9 cm). - **Practical consequence:** a simple petal rule is enough to pick out setosa. Separating versicolor from virginica needs several features together or a multivariate model, and sepal width, which runs against the size ordering, is the feature most likely to add something the size features don't. All three species have exactly 50 specimens, so these differences are not caused by unequal group sizes. These are group summaries (average, min and max), so they show the overlap ranges but not how individual flowers fall within them.