Eduqas A Level Psychology
Eduqas A Level Psychology Inferential Statistics Exam Questions
Free Eduqas A Level Psychology revision for Inferential Statistics: what you need to know, common mistakes and exam-style questions with answers. Covers choosing Chi-square, Mann Whitney U, sign, Spearman's rho and Wilcoxon tests, probability, significance levels and critical values.
Practise Inferential Statistics with past papers
Once you have learnt this topic, find the Inferential Statistics questions in real Eduqas A Level Psychology past papers and mark them with the mark scheme. Doing lots of real questions is the quickest way to learn how examiners ask about each idea.
StemUp mark scheme flashcards
A-Level Psychology Flashcards for 2027 Onwards
Every answer is written in mark scheme wording, so you learn exactly what examiners give marks for. Then test yourself with the questions on this page.
£15.99View flashcards
About Eduqas A Level Psychology Inferential Statistics
Inferential statistics in Component 2 let psychologists decide whether a result is significant or likely to be due to chance. Eduqas requires five tests: Chi-square, Mann Whitney U, the sign test, Spearman's rank order correlation coefficient and Wilcoxon matched pairs signed ranks. You must choose the right test from the design and level of data, understand probability and significance levels, and compare an observed value with a critical value from a table. These questions appear in the principles of research, the personal investigations and the novel scenario sections. Examiners reward a clear justification of the chosen test using all three criteria.
What you need to know
- Choosing a test Ask three questions: is it a test of difference or a correlation; is the design independent or related (repeated measures or matched pairs); and what level of data is it?
- Tests of difference Independent groups: Chi-square (nominal) or Mann Whitney U (ordinal or above). Related designs: sign test (nominal) or Wilcoxon (ordinal or above).
- Correlation and association Spearman's rho tests a correlation between two co-variables with ordinal data or above. Chi-square can also test an association between two nominal variables.
- Probability and significance Psychologists usually use p ≤ 0.05, meaning there is a 5% or lower probability the result is due to chance. A stricter level such as p ≤ 0.01 is used where a mistake would be costly.
- Observed and critical values The observed (calculated) value is compared with the critical value from a table using N (or degrees of freedom) and whether the hypothesis is one or two-tailed. For Chi-square and Spearman's rho the observed value must be equal to or greater than the critical value; for Mann Whitney U, Wilcoxon and the sign test it must be equal to or less than it.
- Type 1 and type 2 errors A type 1 error is rejecting a true null hypothesis (a false positive), more likely with a lenient level such as 0.1. A type 2 error is accepting a false null hypothesis, more likely with a strict level such as 0.01.
Common mistakes in Inferential Statistics
- Justifying a test with only one criterion. Give all three: difference or correlation, design, and level of data.
- Applying the 'greater than' rule to every test. For Mann Whitney U, Wilcoxon and the sign test the observed value must be equal to or less than the critical value.
- Saying a significant result proves the hypothesis. It means the null hypothesis can be rejected at that level; there is still a small probability the result is due to chance.
- Using N as the number of participants in the sign test. Participants with no difference are removed before N is counted.
- Writing 'p = 0.05' instead of 'p ≤ 0.05' when stating the significance level.
Try three Inferential Statistics exam-style questions
1. A researcher uses a repeated measures design and records whether each participant's mood improved (yes or no). Which statistical test should be used? Justify your answer. (3 marks)
Show the mark scheme answer
Sign test; because it is a test of difference; the design is repeated measures (related); and the data are nominal.
2. Five participants are ranked on two co-variables. The sum of d squared is 4. Calculate Spearman's rho using rho = 1 - (6 x sum of d squared) / (n(n squared - 1)). (3 marks)
Show the mark scheme answer
6 x 4 = 24; n(n squared - 1) = 5 x 24 = 120; 24 / 120 = 0.2; rho = 1 - 0.2 = 0.8.
3. Explain what is meant by a type 1 error and when it is more likely. (3 marks)
Show the mark scheme answer
A type 1 error occurs when the null hypothesis is rejected when it is actually true (a false positive); it is more likely when the significance level is too lenient, for example p ≤ 0.1 rather than p ≤ 0.05.
Inferential Statistics FAQs
What does Eduqas A Level Psychology Inferential Statistics cover?
Choosing and interpreting Chi-square, Mann Whitney U, sign test, Spearman's rho and Wilcoxon, plus probability, significance levels and critical values.
Which paper is this examined in?
It is examined in Component 2, Psychology: Investigating Behaviour, a 2 hour 15 minute written paper worth one third of the A level.
How can I remember which test to use?
Use a three-by-two decision grid: rows for nominal, ordinal and interval data, columns for independent, related and correlation, then learn which test sits in each box.
