Hypothesis Testing Week 3

Question 1

What is the central limit theorem?

Answer 1

The theory that, with repeated sampling of a distribution, a distribution will become approximately normal

Question 2

What are the three main concepts of hypothesis testing

Answer 2

• statistically significant difference
• reject/non reject
• can these results be generalised

Question 3

What is sampling error?

Answer 3

The difference between the mean of your sample and the corresponding mean in the population

Question 4

Do smaller or larger samples have a greater likelihood of sampling error?

Answer 4

Smaller

Question 5

What is the null hypothesis?

Answer 5

that your samples come from populations where there is no difference between population means. any difference that is found in the sample is simply due to chance.

Question 6

What is the alternative hypothesis?

Answer 6

You will find a difference

Question 7

Do we test the null or the alternative hypothesis?

Answer 7

The null

Question 8

If we reject the null, we must…

Answer 8

Accept the alternative

Question 9

Describe statistical significance

Answer 9

The likelihood of a result happening that is not due to chance.

Question 10

When do you reject the null hypothesis?

Answer 10

When the likelihood of your means occurring by chance alone is less than .05 (significant)

Question 11

When do you accept the null hypothesis?

Answer 11

When the likelihood of your means occurring by chance alone is over .05, aka there is no significant difference that is due to anything other than chance.

Question 12

What does the p-value tell us?

Answer 12

the probability of getting the data you have given the assumption of the null hypothesis

Question 13

With a p-value of less than .05, we….

Answer 13

Reject the null hypothesis; the difference is significant

Question 14

With a p-value over .05, we…..

Answer 14

Accept the null hypothesis - it must be due to chance.

Question 15

What is reliability?

Answer 15

The degree to which measurements are repeatable or stable over time

Question 16

What is validity?

Answer 16

The scale measures what it is supposed to measure

Question 17

What is content validity?

Answer 17

The degree that the measure reflects the full domain of the construct

Question 18

What is construct validity?

Answer 18

The degree that the measure accurately reflects the construct or concept behind the variable

Question 19

What is face validity?

Answer 19

Does it look valid

Question 20

What is external validity?

Answer 20

Can it be generalised to the broader population

Question 21

What is criterion validity?

Answer 21

The degree to which a measure agrees with a second measure of the same construct

Question 22

How can we minimise sampling error?

Answer 22

Select the sample randomly

Question 23

In every study, we assume that the null is…

Answer 23

true

Question 24

What is Fisherian’s p value used as?

Answer 24

A measure of evidence against the null e.g the smaller the p the less likelihood that the null is true

Question 25

What is Neyman-Pearson’s p value used as?

Answer 25

A simple cut off; reject non reject language; the p value is the probability of a type 1 error.

Question 26

What is a type 1 error?

Answer 26

When you reject the null when it is actually true.