This article covers 3.1.4 Research methods of the AQA GCSE Psychology specification.
Central Tendency: One Number for the Whole Set
- A measure of central tendency tells you the typical value in a set of data.
- You have three to choose from: the mean, the median and the mode.
- Each squeezes a whole dataset into a single number, but which one fits depends on the data.
Key Idea
- All three describe a typical value, but they can disagree, so always name which one you are reporting.
The Mean
- Add up every value, then divide by how many values there are.
- It uses every score, which is a strength, but that also means one extreme score drags it up or down.
The Median
- Put the values in order of size, then take the middle one; with an even number of values, average the middle two.
- Because it ignores how far away the extreme values are, it is the safer choice when a dataset has an outlier.
The Mode
- Find the value that appears most often; when data is grouped into bands, report the modal class, the band with the highest frequency.
- It is the only measure you can use for data in categories, such as favourite subject.
Example
- Seven pupils score 3, 5, 5, 6, 8, 9 and 12 on a recall task. Find all three measures.
- Mean: the scores add to 48, and 48 divided by 7 is 6.86 to two decimal places.
- Median: the values are already in order, and the fourth of seven is the middle, so the median is 6.
- Mode: 5 appears twice and every other value appears once, so the mode is 5.
Choose the Measure That Fits
- Use the mean when the data has no extreme scores and you want every value to count.
- Use the median when an outlier would distort the mean.
- Use the mode for categories or when you simply want the most common result.
Common Mistake
- Do not report the median before you have put the values in order; the raw list rarely gives the true middle.
- Do not report the mean when your data has an extreme outlier without saying it has pulled the figure.
Answer It in Steps
- Calculate the measure the question names, showing each step of your working.
- If asked to choose, match the measure to the data and give a reason.
The Range: How Spread Out Your Data Is
- The range is a measure of spread, also called dispersion.
- You find it by subtracting the lowest value from the highest value.
- It tells you how varied the scores are, not what the typical score is; that job belongs to an average.
Key Idea
- A large range means the data are spread out, while a small range means they cluster tightly together.
Work It Out in Three Steps
- Find the highest value in the dataset.
- Find the lowest value.
- Subtract the lowest from the highest.
Example
- Seven pupils score 3, 5, 5, 6, 8, 9 and 12 on a recall task.
- The highest score is 12 and the lowest is 3.
- Range = 12 minus 3 = 9, so the scores span 9 marks.
One Extreme Value Can Mislead It
Definition
Outlier
A value that lies far away from the rest of the data. It can distort the mean and stretch the range.
- Two classes can share the same mean yet have very different ranges, so the range adds information an average alone hides.
- A small range tells you the group performed consistently, while a large one tells you performance was mixed.
- Its weakness is that a single outlier stretches it a long way, so a range of 9 could hide the fact that six of the seven scores sit within 3 marks.
Common Mistake
- Do not confuse the range, which is spread, with the mean, which is a typical value; they answer different questions.
- Do not report a range without checking whether one outlier has stretched it.
Reporting the Range Well
- Report the range next to an average so the reader sees both the typical value and the spread.
- Be ready both to explain what the range shows and to calculate it as the highest value minus the lowest.
- Whenever you use it to compare two sets, flag any outlier that might be distorting the figure.
Self review
- How do you calculate the mean, the median and the mode?
- Find the mean, median and mode of 2, 4, 4, 7, 8.
- Why is the median better than the mean when there is an extreme score?
- What is the range, and how do you calculate it?