Non-parametric tests

Question 1

What are the assumptions of a parametric analysis?

Answer 1

• Data is (roughly) normally distributed

- There is homogeneity of variance

Question 2

How do non-parametric tests work?

Answer 2

• Based on the principle of ranking the data

- Analysis is then carried out on the ranks rather than the actual data

Question 3

What is the non-parametric equivalent for independent measures t-test?

Answer 3

Mann-whitney or wilcoxon rank-sum

Question 4

What is the non-parametric equivalent for repeated measures t-test

Answer 4

Wilcoxon signed-rank

Question 5

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

Answer 5

Kruskal-wallis

Question 6

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

Answer 6

Friedman’s

Question 7

What do you need to test assumptions?

Answer 7

1. Are your measurements data interval or ratio?
2. Are they normally distributed?
3. Is there homogeneity of variance?

Question 8

Do normality tests need to be non-sig or sig?

Answer 8

sig = no normal distribution (non-parametric test needed)

Question 9

What post-hoc test would you use for a repeated test?

Answer 9

Wilcoxon

Question 10

What post-hoc test would you use for an independent test?

Answer 10

Mann-whitney