A-level Psychology revision · Research methods: data and statistics

Choosing an inferential test

The idea

Choose a test from three questions: is it a test of difference or correlation; is the design related or unrelated; is the data nominal, ordinal or interval? For example, a difference with unrelated design and ordinal data uses Mann-Whitney; a correlation with ordinal data uses Spearman's rho.

  1. Difference or correlation?
  2. Related (repeated measures, matched pairs) or unrelated (independent groups)?
  3. Level of measurement: nominal, ordinal or interval.

Watch out Parametric tests (unrelated t-test, related t-test, Pearson's r) need interval data and roughly normal distributions; the unrelated t-test also needs similar variances.

See it worked

Worked example

Choose a test: independent groups, comparing scores on a 1 to 10 rating scale.

  1. Test of difference.
  2. Unrelated design.
  3. Ordinal data: Mann-Whitney U.

Answer Mann-Whitney U

Your turn

Question 11 mark

A correlation between two sets of interval data that are normally distributed. Which test?

Choose one
Question 21 mark

Repeated measures design with ordinal data. Which test?

Choose one
Question 31 mark

Independent groups with nominal data. Which test?

Choose one

A-level Psychology Pro, AQA 7182

A-level Psychology Pro

£129 once

Price rises to £199 on 1 January. Save £70 by joining before then.

At least 12 months of access

By paying you agree to our Terms and get access straight away, which ends your 14-day cancellation right.

No VAT is charged.