Show Data Variation, Not Design Variation.
Changes in a chart should reflect changes in the data.
Changes in a chart should reflect changes in the data, never changes in design. Inconsistent scales, shifted axes, or variable bin widths create false patterns that mislead even careful readers.
Edward Tufte, 1983 · Principle #3 of Graphical Integrity
Charts that apply this principle
Box Plot
Shows distribution through quartiles, median, whiskers, and outliers.
Ridgeline Plot
Stacked density plots for comparing many distributions, also called Joy Plot.
Hexagonal Grid Map
Equal-sized hexagons represent regions, eliminating area bias.
Tile Grid Map
Each region is a square tile in a grid with equal visual weight and no geographic distortion.
Combo Chart
Overlays bars and lines with dual Y-axes to show volume and rate together.
Radar / Spider Chart
Variables plotted on radial axes from a center point, showing multivariate profiles.
Small Multiples
Same chart repeated for each subset, enabling comparison across a grid of panels.
Calendar Heatmap
Daily values mapped to a calendar grid, revealing day-of-week and seasonal patterns.
Candlestick / OHLC
Shows open, high, low, close for financial data. Each candle is one time period.
Event Timeline
Discrete events as point markers on a single time axis, optionally grouped into lanes — distinct from a Gantt (no bar lengths / durations) and from sparkline-with-annotations (events are the primary mark, not the overlay).