Central Limit Theorem
-
CLT AnimationHow to use
- Drag the Population Shape slider to change what the underlying data looks like.
- Sample Size (n).
- Hit Draw Sample to get the mean.
- Watch that mean drop into the histogram at the bottom.
Population Shape Right-SkewedUniformNormalRight-SkewedLeft-SkewedSample Size (n) 30Draws per Click 10PopulationDistribution of the Sample Mean -
CLT in Words
The Central Limit Theorem (CLT) says: if you repeatedly take random samples of size
nfrom any population and calculate each sample's mean, those sample means will be approximately normally distributed, centered on the true population mean, as long asnis reasonably large. It doesn't matter whether the original population is uniform, skewed, or anything else.Conditions- 1 come from any distribution
- 2 Each observation is independent
- 3
ThenWhy this matters, in practice:- A political poll reports "52% ± 3%", that little margin of error only works because of the CLT.
- A factory checks the average weight of each batch against a target, those checks only make sense because batch averages settle into a predictable bell curve.
- Comparing two versions of a website or product to see which one actually performs better relies on the CLT to tell a real difference from random luck.