choosing a statistical test

Question 1

Levels of measurement

Answer 1

quantitative data can be classified into types or levels of measurement, such as nominal, ordinal and interval

Question 2

Statistical tests

Answer 2

used in psychology to determine whether a significant difference or correlation exists (and consequently, whether the null hypothesis should be rejected or retained).

Question 3

8 statistical tests

Answer 3

• Chi-squared
• Mann-Whitney
• Pearsons r
• Related t-test
• sign test
• Spearman’s rho
• Unrelated test
• Wilcoxon

Question 4

Chi-Squared

Answer 4

a test for an association (difference or correlation) between 2 variables or conditions. Data should be nominal level using an unrelated (independent) design.

Question 5

Mann-Whitney

Answer 5

a test for a significant difference between two sets of scores. Data should be at least ordinal level using an unrelated design (independent groups).

Question 6

Pearson’s r

Answer 6

a parametric test for correlation when data is at interval level

Question 7

Related t-test

Answer 7

a parametric test for difference between 2 sets of scores. Data must be interval with a related design, i.e. repeated measures or matched pairs

Question 8

Sign test

Answer 8

a statistical test used to analyse the difference in scores between related items (e.g. the same participant tested twice). Data should be nominal or better.

Question 9

Spearman’s rho

Answer 9

a test for correlation when data is at least ordinal level

Question 10

Unrelated t-test

Answer 10

a parametric test for difference between two sets of scores. Data must be interval with an unrelated design, i.e. independent groups

Question 11

Wilcoxon

Answer 11

a test for a significant difference between 2 sets of scores. Data should be at least ordinal level using a related design (repeated measures).

Question 12

Difference or correlation?

Answer 12

• first thing to consider when deciding which statistical test to use related to the aim or purpose of the investigation - looking for difference or correlation?
• should be obvious in the wording of hypothesis

Question 13

step 2 of choosing a statistical test

Answer 13

experimental design

Question 14

step 3 of choosing a statistical test

Answer 14

• levels of measurement
• quantitative data can be divided into different levels of measurement and this is the third factor influencing the choice of statistical test — nominal, ordinal and interval

Question 15

Nominal data

Answer 15

data represented in form of categories

- discrete -> one item can only appear in one of the categories.

Question 16

Ordinal data

Answer 16

ordered

• does not have equal intervals between each unit
• lacks precision because it is based on subjective opinion rather than objective measures
• ‘unsafe’ data because lacks precision

Question 17

Interval data

Answer 17

based on numerical scales that include units of equal, precisely defined size.

• better than ordinal data because more detail is preserved
• most precise and sophisticated form of data in psychology