Research methods - Choosing the Right Test

Question 1

Repeated Measures or Matched Pairs Design

Answer 1

Nominal: sign test
Ordinal: Wilcoxon
Interval/Ratio: related t-test

Question 2

Independent Measures Design

Answer 2

Nominal: Chi-Squared test
Ordinal: Mann-Whitney
Interval/Ratio: unrelated t-test

Question 3

Correlation

Answer 3

Nominal: Chi-Squared test
Ordinal: Spearman’s Rho
Interval/Ratio: Pearson’s r

Question 4

Check if your Hypothesis has a Direction

Answer 4

• when looking up critical values it’s important to remember to look back at the hypothesis
• you need to know whether it’s directional or non-directional, so that you can tell whether the test is one-tailed or two-tailed
• it’s also important to remember to check whether your observed value needs to be greater than or less than the critical value for the test you are doing - differs with each statistical test