A sample mean is itself a random number: take another sample and you get another mean. The spread of those means is the standard error (SE):
- For a mean: SE = SD / sqrt(n).
- For a proportion: SE = sqrt(p × (1 - p) / n).
Because of the square root, halving the SE takes four times the data.
The central limit theorem says that, for reasonably large samples, sample means follow a roughly normal distribution even when the data are skewed, like Fenwick Market's order values. You can see it by simulating: draw many samples, take each one's mean, and look at the spread of the means.
The SE is the building block of every confidence interval and test in the units ahead.