4.2.3.3.2 Choosing and using statistical tests Quiz: AQA Psychology, Unit 2

The 20 questions

1. Which test is used to analyse a correlation between two co-variables measured at ordinal level?

   • Pearson's r
   • Spearman's rho
   • Chi-squared test
   • Mann-Whitney U

2. Which test is appropriate for a correlation between two interval-level variables with normally distributed data?

   • Pearson's r
   • Sign test
   • Wilcoxon test
   • Spearman's rho

3. Which test is used to compare two independent groups when the data are ordinal?

   • Mann-Whitney test
   • Related t-test
   • Pearson's r
   • Wilcoxon test

4. Which test is used for a repeated measures design with ordinal data?

   • Spearman's rho
   • Unrelated t-test
   • Mann-Whitney test
   • Wilcoxon test

5. Which test is used to analyse frequency data in categories from independent groups?

   • Pearson's r
   • Related t-test
   • Wilcoxon test
   • Chi-squared test

6. Which test requires interval data, a repeated measures design and normally distributed scores?

   • Sign test
   • Mann-Whitney test
   • Spearman's rho
   • Related t-test

7. What is the key difference between a related and an unrelated design?

   • Related requires nominal data; unrelated requires interval data
   • Related uses different participants in each condition; unrelated uses the same participants
   • Related tests correlation; unrelated tests difference
   • Related uses the same or matched participants in each condition; unrelated uses different participants

8. A psychologist measures hours of revision and exam score for 30 students. Both variables are interval level and normally distributed. Which test should be used?

   • Spearman's rho
   • Chi-squared test
   • Mann-Whitney test
   • Pearson's r

9. Twenty-five students rank their happiness and their stress on the same ordinal scale. Which correlation test is most suitable?

   • Pearson's r
   • Spearman's rho
   • Wilcoxon test
   • Unrelated t-test

10. Two independent groups each give scores on an interval scale that is normally distributed. Which test is appropriate?

    • Pearson's r
    • Unrelated t-test
    • Wilcoxon test
    • Related t-test

11. The same 15 participants are tested before and after a training programme. Their scores are ordinal rankings. Which test is suitable?

    • Wilcoxon test
    • Pearson's r
    • Mann-Whitney test
    • Chi-squared test

12. A researcher counts how many men and women choose each of three brands. The two groups are independent. Which test is most suitable?

    • Chi-squared test
    • Spearman's rho
    • Related t-test
    • Sign test

13. A study compares anxiety ratings given on an ordinal scale by two independent groups of participants. Which test is appropriate?

    • Related t-test
    • Chi-squared test
    • Mann-Whitney test
    • Pearson's r

14. A researcher wants to compare two conditions for the same participants using ordinal data. Which pair of tests are both candidates?

    • Pearson's r or Spearman's rho
    • Wilcoxon or sign test
    • Related t-test or unrelated t-test
    • Mann-Whitney or chi-squared

15. A psychologist has interval data from a repeated measures design, but the scores are clearly not normally distributed. Which test is most appropriate?

    • Unrelated t-test
    • Pearson's r
    • Related t-test
    • Wilcoxon test

16. A researcher applies a chi-squared test to interval-level test scores. What is the best evaluation of this choice?

    • Inappropriate, because chi-squared is designed for frequencies in categories, so the scores need a suitable parametric or rank-based test
    • Appropriate, because interval data is always converted into frequencies first
    • Inappropriate, because chi-squared cannot be used with any kind of data
    • Appropriate, because chi-squared is the only test that works with interval data

17. Why should a researcher not treat ordinal data as if it were interval data when choosing a test?

    • Ordinal data is always easier to analyse with Pearson's r
    • It makes the sample normally distributed automatically
    • It increases the chance of a significant result without any consequences
    • Doing so assumes equal intervals between values that the ordinal scale does not guarantee

18. A study uses normally distributed interval data from two conditions tested on the same participants. Which test and reason are correct?

    • Wilcoxon test, because it always requires ordinal data
    • Spearman's rho, because the two conditions are being correlated
    • Unrelated t-test, because each participant does only one condition
    • Related t-test, because it compares two conditions from the same participants using parametric data

19. Apart from the research hypothesis, which factors most determine the choice of statistical test?

    • The number of hobbies recorded for each participant
    • The name of the researcher who first published the test
    • The colour used to display the results on a graph
    • The level of measurement and the experimental design

20. Using a parametric test on heavily skewed interval data risks which problem?

    • Automatically higher significance
    • A guaranteed Type II error
    • No change to the result, since data type is irrelevant
    • Results that may be misleading because the test's assumptions are violated

Related quizzes

• Learning approaches: behaviourism and classical conditioning Quiz · 4.2.1.1 · 20 questions
• Operant conditioning and social learning theory Quiz · 4.2.1.2 · 20 questions
• The cognitive approach Quiz · 4.2.1.3 · 20 questions
• The biological approach Quiz · 4.2.1.4 · 20 questions
• The psychodynamic approach Quiz · 4.2.1.5 · 20 questions
• Humanistic psychology Quiz · 4.2.1.6 · 20 questions
• Comparison of approaches Quiz · 4.2.1.7 · 20 questions
• Divisions of the nervous system and neurons Quiz · 4.2.2.1 · 20 questions
• Synaptic transmission Quiz · 4.2.2.2 · 20 questions
• Endocrine system and fight or flight Quiz · 4.2.2.3 · 20 questions