The Logic of Null Hypothesis Significance Testing (NHST)

Question 1

What are the 5 steps to NHST?

Answer 1

1. Generate hypotheses (H0 and H1)
   2) Collect data
   3) Evaluate inconsistency of our data with the H0
   4) Reject or fail to reject H0
   5) Interpret

Question 2

What is the 4th step to NHST?

Answer 2

Reject or fail to reject H0

Question 3

What is the 2nd step to NHST?

Answer 3

Collect data

Question 4

What is the 5th step to NHST?

Answer 4

Interpret

Question 5

What is the 1st step to NHST?

Answer 5

Generate hypotheses (H0 and H1)

Question 6

What is the 3rd step to NHST?

Answer 6

Evaluate the inconsistency of our data with H0

Question 7

If the sample mean is closer to the population mean, is it more consistent with H0 or H1?

Answer 7

Consistent with H0
Inconsistent with H1

• Because H0 always argues that there is no difference between our sample mean and the population mean
• And because the sample mean is closer to the pop. mean, it means there is barely any variance aka our sample mean is similar to pop. mean

Question 8

If the sample mean is far away from the population mean, is it more consistent with H0 or H1?

Answer 8

Inconsistent with H0
Consistent with H1

• Because H0 always argues that there is no difference between our sample mean and the population mean
• And because the sample mean is far away from the pop. mean, it means that our sample mean is not similar to pop. mean (more extreme than pop. mean)

Question 9

What do we do with H0 if our results are sufficiently inconsistent with H0?

Answer 9

Reject H0

Question 10

What do we do with H0 if our results are not sufficiently inconsistent with H0?

Answer 10

Fail to reject H0

Question 11

What does it mean when we reject the null/H0?

Answer 11

We have evidence to support the research hypothesis (H1)

Question 12

What does it mean when we fail to reject the null/H0?

Answer 12

We don’t have evidence to support the research hypothesis (H1)

Question 13

If we fail to reject the null (H0) then we can claim to have evidence for the null hypothesis

a. True
b. False

Answer 13

b. False

Just because we fail to find evidence to support H1, does not mean we found evidence to support H0 (We cannot conclude that the sample mean is the exact same as the pop. mean)

Question 14

Fill in the blanks

In order to test our (………..) we need to design an appropriate (…………) that will allow us to recover data from which we can evaluate the extent to which our data is inconsistent with the (………..)

Answer 14

1. Hypotheses
2. Experiment
3. Null hypothesis