Type I And Type II Errors

Question 1

What is a null hypotheses?

Answer 1

‘No difference between conditions’

Question 2

What is an alternative/ experimental hypotheses?

Answer 2

There will be a difference between conditions

Question 3

What hypotheses is rejected for a type 1 error?

Answer 3

The null hypotheses is rejected and alternative hypothesis is accepted when it should be the opposite.

Question 4

Which hypothesis is actually true for a type 1 error?

Answer 4

The null hypothesis

Question 5

What is a type 1 error?

Answer 5

A false positive which claims to have found a significant result when there isn’t one.

Question 6

What hypothesis is accepted for a type 2 error?

Answer 6

The null hypothesis is accepted and the alternative hypothesis is rejected when it should be the other way round.

Question 7

Which hypothesis should actually be accepted for a type 2 error?

Answer 7

The alternative hypothesis

Question 8

What is a type 2 error?

Answer 8

A false negative which claims to have not found a significant result when there is one.

Question 9

When does a type 1 error usually occur?

Answer 9

If the significance is too high/ lenient

Question 10

When does a type 2 error usually occur?

Answer 10

If the significance is too strict/ low

Question 11

What does 0.05 do to the two errors?

Answer 11

Balance them

Question 12

How do you choose a stats test?

Answer 12

• Difference or correlation
• Experimental design
• Level of measurement

Question 13

How do we know if the experiment is difference or correlation?

Answer 13

From the hypothesis

Question 14

What experimental design is used for related design?

Answer 14

• Matched pairs
• Repeated measures

Question 15

What experimental design is used for unrelated design?

Answer 15

• independent measures

Question 16

What are the three levels of measurement which quantitative data can be split into?

Answer 16

1. Nominal data
2. Ordinal data
3. Interval data

Question 17

What is nominal data?

Answer 17

• Categorical
• Discrete = one item can appear in one category

Question 18

What is ordinal data?

Answer 18

Data that is ordered in some way

Question 19

What is interval data?

Answer 19

• Based on numerical scales e.g. units of equal, precisely defined size.
• Usually measurements you’d find in maths or other sciences.

Question 20

What are parametric tests for?

Answer 20

Interval data only

Question 21

What do parametric tests deal with?

Answer 21

Data with a normal distribution

Question 22

What do parametric tests have?

Answer 22

Homogeneity of variance - set of scores in each condition should have similar dispersion or spread

Question 23

Mann Whitney

Answer 23

• Difference
• Unrelated design
  -Ordinal data

Question 24

Wilcoxon

Answer 24

• Difference
• Related design
• Ordinal data

Question 25

Unrelated T-Test

Answer 25

- Difference - Unrelated - Interval data - Parametric test

Question 26

Related T-Test

Answer 26

- Difference - Related design - Interval data - Parametric test

Question 27

Sign Test

Answer 27

- Difference - Related design - Nominal data

Question 28

Spearman’s Rho

Answer 28

- Correlation - Ordinal data

Question 29

Pearson’s R

Answer 29

- Correlation - Interval level data - Parametric test

Question 30

Chi-squared

Answer 30

- Difference or association - Nominal data - Unrelated design