Mistake Master
Student view — seeing the site as a student does
Mistake Master · AP Statistics · Unit 2 · Step-Through Animation

Three Distributions Are in Play, and Only One of Them Goes Normal

You'll learnto keep the population, one sample, and the sampling distribution of a statistic apart, why the sample mean centers on μ with spread σ/√n, what the Central Limit Theorem does and does not promise, and which standard deviation belongs under a z.

A shop logs how many days each repair takes, and the log is strongly right-skewed: most repairs are quick, a few drag on. Sample it and three different distributions are on the table at once. The population has a shape that sampling never touches. One sample of a hundred repairs has a histogram that rebuilds that same skyline — the skew gets clearer with more data, not fainter. And the sample mean, filed across every possible sample, has a third distribution: centered exactly on the population mean, narrower by a factor of the square root of n, and — this is the theorem — approximately normal no matter what the population looks like. This animation builds that third pile by enumerating every sample rather than drawing any, watches the skew drain out of it, and ends on the exam's favorite fork: the same 12.2 ounces asked of one bottle and of an average of sixteen, two answers a factor of thirteen apart.

8 STEPS · 6 QUICK CHECKS · POPULATION vs SAMPLE vs STATISTIC · σ/√n · THE CLT · v1

population fixed · the statistic narrows as √n · only the statistic goes normal
Before you start
What you're looking at
A population of repair times — eight possible durations, most of them short — and, built from it, the exact distribution of the sample mean for samples of 4, 16, 64 and 100.
The question
Three distributions share this study: the population, one sample's data, and the statistic across all samples. Which claims — narrower, unbiased, normal — belong to which?
Watch for
The pile of sample means: it centers on the population mean exactly, its spread halves each time n quadruples, and its skew drains away as 1/√n while the population's never moves.
Step 1 / 8