Tabular and Graphical Representations for the Distributions of Two Categorical Variables
▶︎ Watch it animatedinteractive step-through · ~3 min · optionalA two-way table classifies each individual by two categorical variables at once, with row totals, column totals, and a grand total on the margins. A single cell count yields three different proportions depending on the denominator: joint uses the grand total ($\frac{30}{200}$ of all students are working seniors), conditional uses the group total ($\frac{30}{60}$ of seniors work), and marginal uses a margin over the grand total ($\frac{72}{200}$ of all students work). The wording of the question names the population, and that population's total is the denominator. Segmented bar graphs scale every group to 100% so the segments display the conditional distributions directly; mosaic plots add bar widths proportional to group size; side-by-side bar graphs of raw counts compare group sizes along with everything else.
Two failures repeat. The first is reaching for the wrong total: reporting $\frac{30}{200}$ when asked what fraction of seniors work, or answering "what fraction of workers are seniors" with the fraction of seniors who work, which reverses the condition and changes the answer. The second is judging association from raw cells. With 140 juniors and 60 seniors, juniors contribute more working students (42 versus 30) while working at a far lower rate (30% versus 50%), so the counts and the rates point in opposite directions. Association means the conditional distributions differ across groups, and only a display that puts every group on the same scale can show it.
The work
3 ways in · any order
Lesson
Tabular and Graphical Representations for the Distributions of Two Categorical Variables
›
Sorts out the three proportions a two-way table holds: joint over the grand total, conditional over a group total, marginal over the margin, plus the displays that show conditional distributions and the ones that hide them behind group size.
Diagnostic
10-item topic check
›
Ten items on two-way tables: the wrong total slipped under a conditional, a condition read backward, association claimed from raw cell counts, and bar graphs whose taller bar only records a bigger group. Take it cold to find your habit, or after the lesson to check it is gone.
Targeted Practice
Drill a single misconception
›
Pick one of the failure modes you missed and drill it on its own. The round is adaptive: two correct in a row clears it for now and moves you to the next. Two in a row is a checkpoint, not proof: if the error resurfaces later, the misconception comes back.