Lesson 2.2.3

2.2.3 Analysing experiments: descriptive and inferential statistics Quiz: Pearson Edexcel Psychology, Unit 2

20 questions

Written by Revision Ninja · Last reviewed 11 October 2026

In partnership with Revision Ninja

Lesson 2.2.3, Analysing experiments: descriptive and inferential statistics: 20 multiple choice questions for the Pearson Edexcel Psychology (9PS0), Unit 2: Cognitive psychology, written with Revision Ninja.

Host it live on the board and students join with a game code on their own devices, or revise alone with Free Play. The answers are revealed in the game.

Host this setFree Play

The 20 questions

  1. What is the mean of the recall scores 4, 6, 6, 8 and 11?

    • 8
    • 7
    • 6
    • 11

  2. What is the median of the recall scores 3, 5, 7, 7, 10 and 12?

    • 10
    • 7.5
    • 7
    • 9

  3. What is the range of the recall scores 3, 5, 7, 7, 10 and 12?

    • 9
    • 10
    • 7
    • 12

  4. Which measure of central tendency is best suited to ordinal data such as ranked scores?

    • The mean, since it requires equal intervals between ranks to be calculated and interpreted correctly
    • The median, since it uses the middle position of ordered data without requiring equal intervals
    • The standard deviation, since it describes the spread of the ranks around the mean of the group
    • The range, since it describes the difference between the highest and lowest ranks in the data set

  5. What is the percentage of 18 correct answers out of 24 questions?

    • 80%
    • 72%
    • 75%
    • 67%

  6. Which inferential test is non-parametric and used for an independent groups design?

    • The Mann-Whitney U test
    • The Pearson correlation, which is used to test the strength of a relationship between two continuous variables
    • The Wilcoxon signed-ranks test, which is used for repeated measures designs with related scores
    • The t-test, which is a parametric test that assumes the data are normally distributed in the population

  7. Which inferential test is non-parametric and used for a repeated measures design?

    • The chi-squared test, which is used for categorical frequency data in a contingency table of counts
    • The Wilcoxon signed-ranks test
    • The Mann-Whitney U test, which is used for independent groups designs with unrelated scores
    • The Spearman's rho, which is used to test the strength of a correlation between two sets of ranks

  8. What does a significance level of p≤.05 mean?

    • There is a 5% probability that the alternative hypothesis is true, so the result is weakly supported
    • There is a 5% or lower probability that the result occurred by chance if the null hypothesis is true
    • The sample is 5% of the population, so the result can be generalised to the population with confidence
    • There is a 95% probability that the null hypothesis is true, so the result is almost certain to be correct

  9. A researcher's result has p = .03. Which conclusion is appropriate at the p≤.05 level?

    • The result is significant at p≤.05, so the null hypothesis can be rejected
    • The result proves the alternative hypothesis is true, so no further tests are needed in the study at all
    • The result is significant at p≤.01, so the null hypothesis is proven to be false with complete certainty
    • The result is not significant at p≤.05, so the null hypothesis must be accepted as true for the population

  10. What is a Type I error?

    • Rejecting the null hypothesis when it is actually true, a false positive
    • Accepting the null hypothesis when it is actually false, a false negative in the study's conclusions
    • Using a sample that is too small to show any significant difference between the conditions in the study
    • Using a non-parametric test when a parametric test should be used because the data were normal

  11. What is a Type II error?

    • Recording data with a measurement error, which makes the scores inaccurate across all participants
    • Using the wrong sampling method, which leads to a sample that does not represent the population at all
    • Accepting the null hypothesis when it is actually false, a false negative
    • Rejecting the null hypothesis when it is actually true, a false positive in the conclusions of the study

  12. When should a one-tailed test be used?

    • When the sample is very large, so that the chance of finding a significant result is always reduced
    • When the data are normally distributed, so that a parametric test can be used in every case of research
    • When the hypothesis predicts the direction of the difference, based on clear previous research
    • When the researcher has no prediction about the direction of the difference, so that any change is tested

  13. Which statement about a normal distribution is correct?

    • It is symmetrical, with the mean, median and mode at the centre of the distribution
    • It is uniform, with every score occurring the same number of times across the whole distribution
    • It is skewed to the right, with the mode always lower than the mean and median in the distribution
    • It is skewed to the left, with the mode always higher than the mean and median in the distribution

  14. Which statement about a skewed distribution is correct?

    • Its mean is pulled towards the direction of the tail, away from the mode
    • Its range is always zero, since the scores in a skewed distribution are always identical to each other
    • Its mean, median and mode are always identical, so skew has no effect on any measure of central tendency
    • Its mode is always the largest value in the data set, with a long tail trailing back towards the mean

  15. A researcher finds the Mann-Whitney U value is smaller than the critical value at p≤.05. What should she conclude?

    • The result is not significant, so the null hypothesis must be accepted as true for the population
    • The result is not significant because the sample is too small for any test to be valid at all
    • The result is significant, so the null hypothesis can be rejected at that level
    • The result is significant at p≤.01, which is a stronger level than p≤.05 in every case

  16. Which of these is a benefit of using a descriptive statistic before an inferential test?

    • It proves that the hypothesis is true, so no inferential test is needed to confirm the result in any study
    • It removes the need for any inferential test, because the descriptive values show the answer directly
    • It summarises the data and helps check whether the results make sense before testing them
    • It guarantees that the result is significant, so a significance test is no longer needed in the report

  17. A researcher reports a Mann-Whitney U test result and a Wilcoxon test result for the same data. What is the likely error?

    • No error, since both tests are correlations and are used to measure the strength of relationships in data
    • The wrong test has been used for the design, since Mann-Whitney is for independent groups and Wilcoxon for repeated measures
    • No error, since both tests are parametric and both assume that data are normally distributed in the population
    • No error, since both tests are for repeated measures and can be used interchangeably with the same data

  18. Which of these is the best reason for checking the critical value tables?

    • To decide whether an observed test value is significant at a chosen level of probability
    • To calculate the mean of the data before any statistical test is carried out on the scores in the study
    • To decide which participants should be removed from the sample before the analysis begins in the study
    • To decide which graph to draw to display the frequency of each category in the results section

  19. Which graph is most appropriate for showing the distribution of continuous recall scores?

    • A histogram, with bars touching to show the frequency of scores across a continuous range
    • A bar chart with gaps between bars, which is used for displaying categories such as favourite colours
    • A scatter plot, which is used to show the relationship between two variables for each individual participant
    • A pie chart, which is used to show the proportion of a whole when the categories do not overlap at all

  20. Which test would be used for an independent groups design with ordinal data?

    • Pearson's r, which is a parametric test of correlation that assumes normally distributed continuous data
    • Spearman's rho, which is a test of correlation between two sets of data rather than a test of difference
    • Mann-Whitney U, which is a non-parametric test of difference for independent groups
    • Wilcoxon signed-ranks, which is a non-parametric test of difference for repeated measures designs

All Pearson Edexcel Psychology quizzes