Data Distribution Explorer
Manipulate data-generation conditions and immediately observe changes in distribution shape, spread, skewness, modality, outliers and histogram resolution.
See how distribution shape changes when the data-generating conditions change.
Distribution shape is part of the analytical evidence.
Averages and totals can hide asymmetry, clusters, wide variation and extreme observations. This explorer lets you manipulate meaningful data conditions and observe how those changes affect the histogram and supporting statistics.
The visual is deliberately deterministic: changing one factor produces a repeatable result so the learner can distinguish cause from random redraw noise.
Data Distribution Explorer — Step by Step
Eight locked stages move from a baseline distribution through spread, skewness, outliers, modality, histogram resolution, a contamination challenge and management interpretation.
Distribution Shape, Spread and Structure
Reveal the distribution context to begin.
Distribution interpretation profile
Use these cues to distinguish changes in the underlying data from changes caused only by visualization choices.
Build Your Own Distribution Scenario
Experiment Mode is fully isolated from the guided demonstration. Adjust all eight controls and observe the histogram, shape classification, spread and outlier signals immediately.
Test distribution interpretation.
Distribution interpretation cues
Location
Where the values are centred. Changing location moves the distribution without necessarily changing its shape or spread.
Spread
How dispersed the observations are. Standard deviation and IQR provide different views of variability.
Skewness
Asymmetry in the distribution. Positive skew lengthens the right tail; negative skew lengthens the left tail.
Outliers
Extreme observations may be real, exceptional or erroneous. Investigate cause before deleting or treating them as typical.
Modality
Multiple peaks can indicate distinct subgroups, processes or operating regimes hidden by one summary statistic.
Histogram Bins
Bins change visual resolution, not the underlying observations. Test more than one reasonable setting before concluding the shape is stable.
Use the histogram and supporting statistics together. Separate real changes in the data from visual changes caused by binning or sample size.