How sample means become bell-shaped
Sample from a skewed 0–1 law, a uniform law and an exponential law, and compare each source with its distribution of sample means. After standardisation, see why all of them approach the same bell curve.
- Simulated histogram
- Normal approximation
Source: draw each Xᵢ independently
Distribution of 5000 sample means; the dashed curve is the normal approximation
Sample size n
Mean of the means 0.1SD of the means 0.093Theoretical 0.1 ± 0.095
Source mean μ 0.1SD of the mean σ/√n 0.095
What did you observe?Play first, then answer. Read the explanation only after you have thought it through.
- 1.Choose Bernoulli(p) and look at the histogram at n = 1, then at n = 10, 30 and 100. How do its shape and width change? Is this the same as the original data becoming normal?
- 2.Keep n fixed and switch between the uniform and exponential laws. Which quantity shrinks like 1/√n? Press “Standardised”: what do the three histograms have in common?
- 3.Move Bernoulli p from 0.1 to 0.5. How does the skewness change? Now set p back to 0.1: why does the normal approximation become useful again as n grows?
At n = 1 the sample mean is just one observation, so the histogram has the source's shape. As n grows, averaging many independent terms makes the shape approach a normal curve. What changes is the distribution of the sample mean, not the source itself. If the source has mean μ and variance σ², the sample mean has mean μ and standard deviation σ/√n: quadrupling n halves the width, which is the law of large numbers. Subtract μ and divide by σ/√n, and all three sources give histograms centred near 0 with spread near 1, increasingly resembling the same N(0,1) curve; this is the central limit theorem. Bernoulli with p = 0.5 is relatively symmetric, so the shape looks good even for small n. With p = 0.1 it is strongly skewed, but the variables are still i.i.d. with finite variance, so standardisation leads to normality for large enough n. The 5000 simulated means fluctuate and need not match the theoretical curve exactly.
Related concept: Central limit theorem
Discussion
Found a mistake, have a question or a suggestion? You can also write to 620026600@qq.com
No comments yet. Share your understanding, ask a question, or point out an error on this page.
Log in to join the discussion