All subjects · Psychology · WPS04 Clinical Psychology and Psychological Skills

Descriptive and inferential statistics review (Lists A and B)

Edexcel IAL Psychology · WPS04 Clinical Psychology and Psychological Skills

Spec 9.1.11 (List A) and 9.1.12 (List B) bring together the statistics from the whole course. Formulae are not required, but you must be able to carry out the steps. Calculators are allowed and critical values tables are provided.

Practise this in the app: instant marking and a fix for every mistake. Free, no email needed to start.

Practise this lesson

List A: descriptive statistics

Practice data (invented), scores out of 30: 12, 15, 9, 15, 20, 11, 15, 18, 10, 25.

Mean = 150 / 10 = 15.0; median = 15; mode = 15; range = 25 - 9 = 16.
Standard deviation (spread around the mean) = 4.94.
Here mean = median = mode = 15, which fits a roughly symmetrical spread; in a positive skew a few high scores pull the mean above the median.
Graphs: bar charts for categories, histograms for continuous data (bars touch), scatter diagrams for correlations. Always label axes and give a title.
Normal distribution: symmetrical, mean = median = mode, about 68% within 1 SD of the mean.

List B: choosing and using tests

Levels of measurement: nominal (categories), ordinal (ranks), interval/ratio (equal units).
Test choice: Wilcoxon (difference, related, ordinal+); Spearman (relationship, ordinal+); chi-squared (difference or association, independent, nominal).
Significance levels: p ≤ .10, p ≤ .05 (the usual level in psychology), p ≤ .01. p ≤ .05 means there is a 5% or less probability the result is due to chance.
Observed vs critical value: Wilcoxon T must be ≤ critical; Spearman rs and chi-squared must be ≥ critical.
One-tailed for directional hypotheses, two-tailed for non-directional.
Sense-check: rs must lie between -1 and +1; T cannot be larger than the total of the ranks.

Type I and Type II errors

Error	What happens	More likely when
Type I (false positive)	Rejecting the null hypothesis when it is true	The significance level is too lenient (for example p ≤ .10)
Type II (false negative)	Accepting the null hypothesis when it is false	The significance level is too strict (for example p ≤ .01)

Spearman example

Practice data (invented): hours of sleep and stress scores for 8 people.

Sleep: 3, 7, 5, 9, 2, 8, 6, 4; Stress: 14, 9, 12, 6, 15, 7, 11, 10.

Ranks: 2, 6, 4, 8, 1, 7, 5, 3 and 7, 3, 6, 1, 8, 2, 5, 4. Σd² = 162.

rs = 1 - 6 x 162 / (8 x 63) = -0.929. Critical value (N = 8, two-tailed p ≤ .05) = 0.738. |rs| ≥ critical, so a significant negative correlation. Remember the minus sign: the June 2025 examiners deducted a mark for leaving it out.

Worked example

For the scores [12, 15, 9, 15, 20, 11, 15, 18, 10, 25], calculate the mean and standard deviation, and explain what the standard deviation shows.

Mean = 150 / 10 = 15.0.
Standard deviation: find each score's deviation from the mean, square, sum, divide by n - 1 = 9, square root = 4.94.
The SD shows the average spread of scores around the mean; a larger SD means scores are more varied.

Answer: Mean 15.0, SD 4.94.

Key idea: List A: mean, median, mode, range, SD, tables, bar charts, histograms, scatter diagrams, normal and skewed distributions, percentages. List B: levels of measurement, test choice, significance levels, observed vs critical, one- and two-tailed, Type I and II errors.

Check yourself

Calculate the mean of these scores: 12, 15, 9, 15, 20, 11, 15, 18, 10, 25. Give your answer to 1 decimal place.
Show answer
15.0. Sum = 150; 150 / 10 = 15.0.
Calculate the standard deviation of the same scores (sample formula, n - 1) to 2 decimal places.
Show answer
4.94. SD = 4.94.
Calculate Spearman's rs for the sleep and stress data in step 4 to 3 decimal places.
Show answer
-0.929. Σd² = 162; rs = 1 - 6 x 162 / 504 = -0.929.
What is the median of the scores in step 1?
Show answer
15. Ordered: [9, 10, 11, 12, 15, 15, 15, 18, 20, 25]; the middle two are 15 and 15, so the median is 15.
A researcher rejects the null hypothesis when it is actually true. This is a
- Type II error
- one-tailed test
- sampling bias
- Type I error
Show answer
Type I error. False positive.
Which significance level makes a Type I error most likely?
- p ≤ .05
- p ≤ .10
- p ≤ .01
- p ≤ .001
Show answer
p ≤ .10. A lenient level accepts results more likely to be due to chance.
Which graph is most suitable for continuous data such as reaction times grouped into intervals?
- Bar chart
- Scatter diagram
- Pie chart
- Histogram
Show answer
Histogram. Histogram bars touch because the data are continuous.
In a positively skewed distribution, the mean is usually
- lower than the median
- equal to the mode
- higher than the median
- zero
Show answer
higher than the median. The tail of high scores pulls the mean up.

Practise with instant feedback

Sources

Last updated 8 November 2026. Spotted a mistake? Tell us.