Mistake Master
Student view — seeing the site as a student does
Mistake Master · AP Statistics · Unit 3 · Step-Through Animation

Every Rule in the Setup Is a Promise About How Often You Are Wrong

You'll learnwhy both hypotheses are claims about the parameter and never about the sample, where the alternative's direction comes from, why the conditions and the standard error use the hypothesized proportion, what the significance level is committing to — and what each of those rules costs in false alarms when it is broken after the data arrive.

A company claims 40% of its customers renew. A manager suspects it is lower, surveys 250 randomly chosen customers, and finds 88 renewals — a sample proportion of 0.352. Setting up the test means writing four things down before any of that arithmetic happens: the parameter in context, the two hypotheses, the conditions with their numbers, and the significance level. Those rules sound like etiquette, and this page prices them instead. Under a null that is exactly true, a one-sided test at the 5% level rejects 5.24% of the time — as advertised. Choose which tail to use after seeing which way the sample fell, and the same test rejects 10.64% of the time: a promise of one false alarm in twenty, delivering one in nine. And this sample's p-value is 0.0607, sitting between the two most common significance levels, so a level chosen after the fact decides the verdict by itself.

8 STEPS · 6 QUICK CHECKS · HYPOTHESES ABOUT p · THE DIRECTION · CONDITIONS WITH p0 · ALPHA IN ADVANCE · v1

the null's own distribution · shopping the tail doubles the false alarms to 10.6% · p = 0.0607, between the levels
Before you start
What you're looking at
The exact distribution of the sample proportion in the world where the company's claim is true: p = 0.40, n = 250. The observed 0.352 is drawn on it in amber.
The question
A setup is four decisions made before the data are read. What does each one actually commit to, and what changes if it is made afterwards instead?
Watch for
The shaded region. Every rule in the setup is really a rule about how much of the null's own distribution counts as evidence against it.
Step 1 / 8