Hover ribbons to see flow details · Click a category block to isolate its paths · Colour by any dimension
Parallel Sets encode the joint distribution of multiple categorical variables simultaneously. Each dimension is represented as a vertical axis; the categories within each dimension appear as proportional segments (blocks) on that axis. Ribbons connect adjacent dimensions: each ribbon represents the population subset that belongs to a specific category in dimension A and a specific category in dimension B. Ribbon width is proportional to that subset's count.
The key perceptual mechanism is width-along-a-common-baseline: the viewer reads the relative size of each ribbon as a proportion of the total at any given axis crossing. The flow direction is left-to-right, and at each axis the full width of all incoming ribbons equals the full width of the category block — the chart is mass-conserving.
Both charts use proportional ribbon widths to show flow. The critical difference is structural. A Sankey Diagram shows flows between nodes in an arbitrary network — nodes can appear at any position, flows can cross and split in any direction, and the topology is defined by the data's actual directed graph. It is designed for process flows: energy systems, supply chains, user journeys with multiple possible paths.
A Parallel Sets chart imposes a strict rectangular axis structure. Every dimension occupies a vertical column; every category within a dimension occupies a proportional block on that column. Ribbons only connect adjacent columns — there are no backwards flows, no skipped dimensions. This structure enforces comparability: the viewer can scan vertically at any axis and read the marginal distribution of that dimension, then read ribbons horizontally to understand joint distributions.
The message involves the joint relationship between three categorical variables: Education, Employment Status, and Income. These are not process steps in a causal sequence — they are co-occurring attributes of a population. The question is distributional: "what proportion of the population occupies each combination of these three categories?"
A grouped bar chart could show one pairwise relationship at a time but would require six separate charts to cover all dimension pairs. A mosaic plot (Marimekko) could show two dimensions simultaneously. Parallel Sets handles three or more dimensions in a single view without losing the proportional encoding or introducing the dimension-ordering artefacts of a Parallel Coordinates Plot.
A Parallel Coordinates Plot — the visually closest alternative — encodes each observation as a polyline crossing multiple continuous axes. It is designed for continuous data: each observation's exact value on each axis is plotted and connected. Applied to categorical data, all observations within a category collapse to the same line, producing overplotted bands that are indistinguishable from one another without transparency hacks. Parallel Sets solves this by encoding aggregated counts as ribbon widths rather than individual observations as lines.
A Sankey Diagram would work but implies directionality and process. Showing Education → Income as a Sankey implies that education causes income through a flow process. Parallel Sets makes no such implication — it shows co-occurrence, not process, and the rectangular axis structure signals correlation rather than causation.
FT Visual Vocabulary — Part-to-Whole / Flow (hybrid). Parallel Sets sits at the intersection of these two FT categories: it shows how a whole population distributes across categorical combinations (part-to-whole) while using ribbon width to indicate flow magnitude between adjacent dimensions (flow). Abela quadrant: Distribution (multiple categorical variables, joint). Tufte principle: no axis truncation — the full height of each dimension column represents 100% of the population, and all ribbon widths sum to the column height at every dimension. The one design decision worth knowing: colour is assigned to the first dimension by default, making the origin category the primary reading frame. Switching colour to income (right axis) inverts the reading direction, revealing which income outcomes dominate each education-employment combination rather than where each education cohort ends up.