Cumulative Frequency
Cumulative frequency is the running total of frequencies built up through a grouped frequency table, and a cumulative frequency graph plots these running totals against the upper boundary of each class to give a smooth curve.
Before you start
Make sure you're comfortable with these topics first:
Method
- Add a cumulative frequency column to the grouped frequency table by adding each class's frequency to the running total of all classes before it.
- Plot each cumulative frequency against the upper class boundary of its class interval, not the midpoint.
- Join the plotted points with a smooth curve or straight lines, starting from a cumulative frequency of 0 at the lower boundary of the first class.
- To estimate the median, find the value halfway up the cumulative frequency axis, draw across to the curve, then down to the horizontal axis.
- To estimate the lower or upper quartile, use one quarter or three quarters of the way up the cumulative frequency axis in the same way.
- To estimate how many items are above or below a given value, draw a line up from that value to the curve, then across to the cumulative frequency axis and read off the value.
Common mistakes
MistakePlotting cumulative frequency against the midpoint of each class interval, as for a frequency polygon, instead of the upper class boundary.
InsteadAlways plot against the upper class boundary: for a class 40-50 with cumulative frequency 38, the point plotted is (50, 38), not (45, 38), which is that class's midpoint.
MistakeReading across from the wrong cumulative frequency value when estimating the median or a quartile, for example using the total number of data values (n) instead of n/2 for the median.
InsteadState the correct value before reading across: for 200 data values, the median is read at cumulative frequency 200/2 = 100, not at 200, which would read off the very top of the curve instead of the middle.
MistakeFinding 'the number of values above a given point' by reading off the cumulative frequency at that point and stopping there, instead of subtracting it from the total.
InsteadSubtract from the total frequency: if a cumulative frequency of 54 corresponds to a value of 25 out of 120 total data values, the number of values above 25 is 120 - 54 = 66, not 54, which is the number of values below or at that point.
Worked examples
Example 1
The table shows the cumulative frequency for the times, in minutes, taken by 60 students to complete a puzzle: under 10 minutes: 8 students, under 20 minutes: 26 students, under 30 minutes: 46 students, under 40 minutes: 56 students, under 50 minutes: 60 students. Use the cumulative frequency graph to estimate the median time.
- There are 60 students in total, so the median is found at the point halfway up the cumulative frequency axis, which is 60/2 = 30.
- Draw a line across from a cumulative frequency of 30 to meet the cumulative frequency curve.
- The curve passes from 26 (at 20 minutes) to 46 (at 30 minutes), so a cumulative frequency of 30 falls a small way into this interval.
- Reading down from that point on the curve to the horizontal axis gives an estimated time of approximately 22 minutes.
- Final answer: the estimated median time is approximately 22 minutes.
Example 2
A cumulative frequency table for the times, in minutes, taken by 150 runners to finish a race is: under 40 min, 12 runners; under 50 min, 38 runners; under 60 min, 97 runners; under 70 min, 135 runners; under 80 min, 150 runners. (a) Estimate how many runners took between 50 and 60 minutes. (b) A 'fast finisher' medal requires a time under 50 minutes, and organisers have budgeted for 30 medals. Based on this data, is 30 medals likely to be enough?
- Runners under 60 minutes = 97 (given). Runners under 50 minutes = 38 (given).
- Runners between 50 and 60 minutes = 97 - 38 = 59.
- Runners under 50 minutes, the 'fast finishers', number 38, read directly from the table.
- Since 38 runners qualify but only 30 medals are budgeted, 30 medals is not enough.
- Final answer: an estimated 59 runners took between 50 and 60 minutes, and 30 medals would not be enough, since 38 runners qualify as fast finishers.
Example 3
A second company, Company Y, publishes a summary of its employees' annual salaries: median £42,000 and interquartile range £12,000. Using your estimates for Company X from Question 10 (median £40,000, interquartile range £18,000), compare the two companies' salaries. Give your answer in the context of the question.
- The median describes the typical salary. Company Y's median is £42,000, compared with £40,000 for Company X, so Company Y has the higher typical salary.
- The interquartile range describes the spread of the middle half of salaries.
- Company Y's IQR is £12,000, compared with £18,000 for Company X. The smaller IQR describes less variation in the middle half of Company Y's salaries.
- These are comparisons of the typical salary and the middle half only; they do not show that every employee earns more or describe the full range of salaries.
- Final answer: Company Y has a higher median salary and a smaller IQR than Company X, so its typical salary is higher and the middle half of its salaries varies less.
Practice questions
Q1[1 mark]On a cumulative frequency graph, what do you plot each cumulative frequency against?Show answer
Answer: The upper class boundary of its class interval.
Q2[2 marks]A frequency table has class frequencies 5, 9, 14, 7 for four consecutive classes. Find the cumulative frequency of the third class.Show answer
Answer: 28 (5 + 9 + 14 = 28).
Q3[2 marks]A cumulative frequency graph for 80 data values is used to estimate the median. At what cumulative frequency value do you read across to the curve?Show answer
Answer: 40 (half of 80).
Q4[2 marks]For 80 data values, at what cumulative frequency do you read across to find the lower quartile?Show answer
Answer: 20 (one quarter of 80).
Q5[2 marks]A cumulative frequency graph shows that a cumulative frequency of 45 corresponds to a value of 60 on the horizontal axis, out of 90 total data values. How many data values are above 60?Show answer
Answer: 45 (90 - 45 = 45 values are above 60).
Q6[2 marks]Explain why a value read from a cumulative frequency graph, such as the median, is described as an estimate rather than an exact value.Show answer
Answer: The original data was grouped into class intervals, so the exact individual values within each class are unknown; the graph only shows running totals at class boundaries.
Exam-style questions
Written in the style of a GCSE Statistics exam paper, with a full mark scheme.
Exam tips
- Plot cumulative frequency against the upper boundary of each class, never the midpoint - the running total by definition includes everything up to that upper edge.
- State the cumulative frequency value you are reading across from (n/2 for the median, n/4 for the lower quartile, 3n/4 for the upper quartile) as its own line of working, separate from the estimate read off the graph.
- To find how many values lie above a point, or between two points, subtract cumulative frequencies (from the total, or from each other), rather than reading off and stopping at a single value.
Q1[3 marks]120 apples are weighed and grouped by mass. The cumulative frequency table shows: under 100g: 10 apples, under 120g: 40 apples, under 140g: 85 apples, under 160g: 110 apples, under 180g: 120 apples. Use the cumulative frequency graph to estimate the median mass.Show mark scheme
Tick each line you got.
Nothing ticked yet - 3 available
Q2[4 marks]Using the apple data in the previous question, estimate the interquartile range.Show mark scheme
Tick each line you got.
Nothing ticked yet - 4 available
Q3[2 marks]Explain why the cumulative frequency curve should always be non-decreasing (it never goes down) as you move from left to right.Show mark scheme
Tick each line you got.
Nothing ticked yet - 2 available
See real GCSE Statistics past-paper questions, with official mark schemes
This topic in real past papers
We have tagged some boards' past papers question by question (not every board or year yet). This topic comes up in:
- AQA GCSE Statistics past papers: 8 questions across 8 papers, latest tagged June 2023
- Edexcel GCSE Statistics past papers: 5 questions across 5 papers, latest tagged June 2022
Free printable worksheet
Want more practice on paper? Download the Cumulative Frequency worksheet pack - 38 pages of exam-style questions with a full mark scheme. Free to download, no card or account. Print it for personal and classroom use.
This topic is chapter 21 of GCSE Statistics Foundation Essentials 1 and chapter 25 of GCSE Statistics Higher Essentials 1, the whole course as one free printable PDF. Its worksheet is also chapter 5 of GCSE Statistics Foundation Topic Workbook 3 and chapter 3 of GCSE Statistics Higher Topic Workbook 4, free printable practice books.
Other versions of this worksheet: