Distribution Lab
Sample from seven distributions, watch the central limit theorem happen at whatever sample size you choose, and see exactly when the mean stops being a useful summary.
Loading…
About this tool
Most statistical intuition is built by watching sampling distributions move. This lets you do that directly: change the population, change n, redraw, and watch the sampling distribution of the mean tighten and straighten out — or, for a heavy enough tail, stubbornly refuse to.
Worth knowing
- Try lognormal with n = 5, then n = 200. That gap is why "the CLT handles it" is not always true.
- The mean and median markers are drawn on every histogram. Watch them separate as skew increases.
- Everything is seeded, so you can reproduce any picture you generate.