Hypothesis testing

What you'll learn

1. 1

   Imagine you're a detective 🕵️. You have a theory that a coin is fair (lands heads 50% of the time). You flip it 20 times and get 15 heads — is that just bad luck, or is the coin unfair?

2. 2

   Flip this virtual coin 20 times. How many heads do you get?

3. 3

   Let's test if a coin is fair. We flip it 10 times and get 8 heads. Is that unusual?

4. 4

   What is the null hypothesis in this coin-flip example?

5. 5

   Now flip the coin 30 times. You get 22 heads. Use the number line to see where 22 heads falls — is it far from 15 (the expected number if fair)?

6. 6

   We set a 'significance level' of 5% (p < 0.05). That's like saying: 'If the chance of this result is less than 5%, we reject the null hypothesis.'

7. 7

   If the probability of your result is 3% and your significance level is 5%, what do you do?