Unit 10 - Power

Question 1

Power

Answer 1

P(rejecting null | null false)
P(not making Type II error)
P(correctly rejecting the null)
P(detecting an effect if it exists)

Question 2

Type I error

Answer 2

A false positive—when you reject the null hypothesis (there is an effect) when the null hypothesis is true (there isn’t an effect)

Question 3

Type II error

Answer 3

A false negative—when you accept the null hypothesis (there isn’t an effect) when the null hypothesis isn’t true (there is an effect)

Question 4

What happens if you increase the significance level (ex: from 0.01->0.05)?

Answer 4

The power increases and the probability of a type II error goes down

The probability of making a type I error increases (because you are more likely to reject the null when it is true)

Question 5

What happens if you decrease the significance level (ex: from 0.05->0.01)?

Answer 5

The power decreases and the probability of a type II error goes up

The probability of making a type I error decreases (because you are less likely to reject the null when it is true)

Question 6

How do various things affect power?

Answer 6

Power increases with the significance level (if the significance level goes from 0.05–>0.1, power increases as well)
Power increases with sample size
Power increases as the true population parameter moves farther away from the null parameter