Distribution Visualizer

What it does

The Distribution Visualizer samples a probability distribution and draws the result as an accessible histogram — the fastest way to see what normal, uniform, or skewed data actually looks like. Choose a distribution, draw up to 10,000 samples into 2–50 bins, and reuse a seed to freeze the exact chart.

Common use cases

• Teaching statistics — show the bell curve emerge: 30 samples look ragged, 10,000 look like the textbook.
• Explaining sample size — same distribution, different n, side by side; the single most convincing argument for bigger samples.
• Choosing bin counts — demonstrate how too few bins hide structure and too many manufacture noise.
• Prototyping — a quick visual check of what simulated input data will look like before building a full pipeline.

Settings

• Distribution — the family to sample from.
• Samples — 1 to 10,000 draws; more samples = smoother histogram.
• Bins — 2 to 50 histogram buckets.
• Seed — the same seed and settings always reproduce the identical sample and chart — ideal for worksheets where everyone should see the same figure.

Privacy note

Samples are computed locally in your browser and never uploaded. The data is synthetic draws from ideal mathematical distributions — not measurements of anything real.

FAQ

Why does my histogram look lumpy? Small samples are noisy — that’s a feature for teaching. Raise the sample count and watch the shape converge to the ideal curve.

How many bins should I use? A common rule of thumb is √n bins; in practice 10–20 works for most classroom-sized samples. Try a few — comparing them is itself a lesson.

Can I export the underlying data? Yes — the sample exports as CSV or JSON, so students can rebuild the histogram in a spreadsheet and verify the tool.

Where do I get raw samples without the chart? The Distribution Sampler generates the numbers alone, with more distributions and parameter control.