Non parametric statistics

Question 1

What assumptions do parametric statistics make?

Answer 1

Assumptions about the population from which the sample has been drawn

Question 2

Makes assumptions about the population from which the sample has been drawn

a. Parametric statistics
b. Non-parametric statistics

Answer 2

a. Parametric statistics

Question 3

Do not make assumptions about the underlying population distributions

a. Parametric statistics
b. Non-parametric statistics

Answer 3

b. Non-parametric statistics

Question 4

Known as distribution-free statistics

a. Parametric statistics
b. Non-parametric statistics

Answer 4

b. Non-parametric statistics

Question 5

True or False?

Non-parametric tests have less power than their parametric equivalents

Answer 5

True

Question 6

Using non-parametric tests results in higher risk of…?

a. Type II error
b. Type I error

Answer 6

a. Type II error

Question 7

What is the non-parametric equivalent of an independent t-test?

Answer 7

Mann-Whitney U test

Question 8

What is the non-parametric equivalent of a paired t-test?

Answer 8

Wilcoxon T Test

Question 9

What is the non-parametric equivalent of a one-way independent ANOVA?

Answer 9

Kruskal Wallis Test

Question 10

What is the non-parametric equivalent of a one-way repeated measures ANOVA?

Answer 10

Friedman Test

Question 11

What is the non-parametric equivalent of a two-way independent ANOVA?

Answer 11

No non-parametric equivalent

Question 12

What is the non-parametric equivalent of a two-way repeated measures ANOVA?

Answer 12

No non-parametric equivalent

Question 13

What is the non-parametric equivalent of a two-way mixed ANOVA?

Answer 13

No non-parametric equivalent

Question 14

An experiment has 1 IV with 2 levels between subjects but normality assumptions have not been met

Which statistic is used?

a. Kruskal Wallis Test
b. Friedman Test
c. Mann-Whitney U Test
d. Wilcoxon T Test
e. No non-parametric equivalent

Answer 14

c. Mann-Whitney U Test

Question 15

An experiment has 1 IV with 2 levels within subjects but normality assumptions have not been met

Which statistic is used?

a. Kruskal Wallis Test
b. Friedman Test
c. Mann-Whitney U Test
d. Wilcoxon T Test
e. No non-parametric equivalent

Answer 15

d. Wilcoxon T Test

Question 16

An experiment has 1 IV with more than 2 levels within subjects but normality assumptions have not been met

Which statistic is used?

a. Kruskal Wallis Test
b. Friedman Test
c. Mann-Whitney U Test
d. Wilcoxon T Test
e. No non-parametric equivalent

Answer 16

b. Friedman Test

Question 17

An experiment has 1 IV with more than 2 levels between subjects but normality assumptions have not been met

Which statistic is used?

a. Kruskal Wallis Test
b. Friedman Test
c. Mann-Whitney U Test
d. Wilcoxon T Test
e. No non-parametric equivalent

Answer 17

a. Kruskal Wallis Test

Question 18

An experiment has 2 IVs between subjects but normality assumptions have not been met

Which statistic is used?

a. Kruskal Wallis Test
b. Friedman Test
c. Mann-Whitney U Test
d. Wilcoxon T Test
e. No non-parametric equivalent

Answer 18

e. No non-parametric equivalent

Question 19

An experiment has 2 IVs within subjects but normality assumptions have not been met

Which statistic is used?

a. Kruskal Wallis Test
b. Friedman Test
c. Mann-Whitney U Test
d. Wilcoxon T Test
e. No non-parametric equivalent

Answer 19

e. No non-parametric equivalent

Question 20

An experiment has 2 IVs mixed subjects but normality assumptions have not been met

Which statistic is used?

a. Kruskal Wallis Test
b. Friedman Test
c. Mann-Whitney U Test
d. Wilcoxon T Test
e. No non-parametric equivalent

Answer 20

e. No non-parametric equivalent

Question 21

How do we check that the normality assumption is met for independent designs?

Answer 21

The DV should be normally distributed, under each
level of the IV

Question 22

How do we check that the normality assumption is met for repeated measures designs?

Answer 22

The DV difference scores should be normally
distributed, between each paired level of the IV

Question 23

The DV should be normally distributed, under each
level of the IV

a. Repeated measures
b. Independent

Answer 23

b. Independent

Question 24

The DV difference scores should be normally
distributed, between each paired level of the IV

a. Repeated measures
b. Independent

Answer 24

a. Repeated measures

Question 25

How can we assess the normality assumption statistically?

Answer 25

Using Shapiro-Wilk test

Question 26

What is the Shapiro-Wilk test for?

Answer 26

Assessing normality assumption statistically

Question 27

List 3 parametric tests of relationships

Answer 27

1. Pearson’s correlation coefficient 2. Partial correlation 3. Regression

Question 28

What are the non-parametric equivalents of Pearson’s correlation coefficient?

Answer 28

1. Spearman’s rho Used where N > 20 2. Kendall’s Tau Used where N < 20

Question 29

What are the non-parametric equivalents of partial correlation?

Answer 29

There are none

Question 30

What are the non-parametric equivalents of regression?

Answer 30

There are none

Question 31

List 7 parametric tests of differences

Answer 31

1. Independent t-test 2. Paired t-test 3. One-way independent ANOVA 4. One-way repeated measures ANOVA 5. Two-way independent ANOVA 6. Two-way repeated measures ANOVA 7. Two-way mixed ANOVA

Question 32

List 4 non-parametric tests of differences

Answer 32

1. Mann-Whitney U 2. Wilcoxon T Test 3. Kruskal Wallis Test 4. Friedman Test

Question 33

Spearman’s rho is the non-parametric equivalent of Pearson’s correlation coefficient for...? a. Used where N < 20 b. Used where N > 20

Answer 33

b. Used where N > 20

Question 34

Kendall's Tau is the non-parametric equivalent of Pearson’s correlation coefficient for...? a. Used where N < 20 b. Used where N > 20

Answer 34

a. Used where N < 20

Question 35

Name the non-parametric equivalent for Pearson's correlation coefficient when N < 20

Answer 35

Kendall’s Tau

Question 36

Name the non-parametric equivalent for Pearson's correlation coefficient when N > 20

Answer 36

Spearman’s rho

Question 37

Should we use parametric or non-parametric when testing for relationships in this scenario? Either variable is measured on an ordinal scale

Answer 37

Non-parametric

Question 38

True or False? It is best to use parametric if either variable is measured on an ordinal scale (especially if you are concerned that the intervals between measures are not equivalent)

Answer 38

False It is best to use non-parametric if either variable is measured on an ordinal scale (especially if you are concerned that the intervals between measures are not equivalent)

Question 39

When should we use non-parametric tests of relationships other than when the normality assumption is not met?

Answer 39

If either variable is measured on an ordinal scale (especially if you are concerned that the intervals between measures are not equivalent)

Question 40

What are the 2 tests we can run to analyse categorical data?

Answer 40

1. One-variable Chi-Square (a.k.a. Goodness of Fit Test 2. Chi-Square Test of Independence (two variables)

Question 41

The Chi-Square Test with two variables is known as...?

Answer 41

Chi-Square Test of Independence

Question 42

What is the Chi-Square Test of Independence?

Answer 42

Analysis of categorical data with two variables

Question 43

Analysis of categorical data with two variables This is known as...?

Answer 43

Chi-Square Test of Independence

Question 44

The Goodness of Fit Test is also known as...?

Answer 44

One-variable Chi-Square

Question 45

What is the One-variable Chi-Square?

Answer 45

Analysis of categorical data with one variable AKA Goodness of Fit Test

Question 46

Analysis of categorical data with one variable AKA Goodness of Fit Test This is known as...?

Answer 46

One-variable Chi-Square

Question 47

What is the non-parametric equivalent for One-variable Chi-Square?

Answer 47

There are none

Question 48

What is the non-parametric equivalent for the Chi-Square Test of Independence?

Answer 48

There are none

Question 49

Why are there no non-parametric equivalents for the One-variable Chi-Square (a.k.a. Goodness of Fit Test) and Chi-Square Test of Independence?

Answer 49

If the DV (outcome variable) is measured on a categorical scale, non-parametric tests are the only option