Box Plots from Cumulative Frequency and Outliers
A box plot built from cumulative frequency data is a diagram showing the five-number summary, minimum, lower quartile, median, upper quartile and maximum, estimated from a cumulative frequency graph rather than raw data. An outlier is a value more than 1.5 times the interquartile range beyond a quartile, marked as a separate point rather than at the end of a whisker. This is assessed on GCSE Statistics Higher tier.
Before you start
Make sure you're comfortable with these topics first:
Method
- From a cumulative frequency graph or table, estimate the median (position n/2), lower quartile (position n/4) and upper quartile (position 3n/4), interpolating within grouped data if needed.
- Record the five-number summary: minimum, lower quartile, median, upper quartile, maximum.
- Calculate the interquartile range: IQR = Q3 - Q1.
- Calculate the outlier boundaries: lower boundary = Q1 - 1.5 x IQR, upper boundary = Q3 + 1.5 x IQR.
- Test the minimum, maximum and any other suspicious values against these boundaries: any value beyond a boundary is an outlier.
- Draw the box plot with the box from Q1 to Q3 (median marked inside), whiskers extending to the most extreme values that are NOT outliers, and outliers marked individually beyond the whiskers.
Common mistakes
MistakeUsing the wrong cumulative frequency position for a quartile, for example using n/4 for the median instead of n/2, especially when interpolating from a table.
InsteadState each position before reading the table: for n=200, the median position is 200/2 = 100, not 200/4 = 50, which is actually the lower quartile's position.
MistakeCalculating only the upper outlier boundary and checking the maximum, while forgetting to also calculate the lower boundary and check the minimum.
InsteadCheck both ends: for Q1=50, Q3=80 (IQR=30), the upper boundary is 80+45=125 and the lower boundary is 50-45=5; a minimum of -2 is below 5, so it is also an outlier, which only checking the upper boundary would miss.
MistakeDrawing or describing the whisker as extending all the way to the most extreme data value, even after that value has been identified as an outlier.
InsteadStop the whisker at the most extreme non-outlier value: if a maximum of 102 is an outlier and the next-highest non-outlier value is 85, the whisker extends only to 85, with 102 plotted as a separate point beyond it.
Worked examples
Example 1
The cumulative frequency table below shows delivery times, in minutes, for 80 parcels: 0 < t <= 20, frequency 10; 20 < t <= 40, frequency 20; 40 < t <= 60, frequency 40; 60 < t <= 100, frequency 10. The minimum delivery time was 2 minutes and the maximum was 95 minutes. Estimate the quartiles, then determine whether the minimum and maximum should be plotted as outliers.
- With n = 80, the lower quartile is at position n/4 = 20, the median at position n/2 = 40, and the upper quartile at position 3n/4 = 60.
- The cumulative frequencies are 10, 30, 70, 80 at the class boundaries 20, 40, 60, 100. The lower quartile falls in the class 20 < t <= 40 (cumulative frequency 10 to 30): Q1 = 20 + (20 - 10)/20 x 20 = 30 minutes.
- The median falls in the class 40 < t <= 60 (cumulative frequency 30 to 70): median = 40 + (40 - 30)/40 x 20 = 45 minutes.
- The upper quartile also falls in the class 40 < t <= 60: Q3 = 40 + (60 - 30)/40 x 20 = 55 minutes.
- IQR = 55 - 30 = 25. Lower boundary = 30 - 1.5 x 25 = -7.5. Upper boundary = 55 + 1.5 x 25 = 92.5. The minimum (2) is above -7.5, so it is not an outlier; the maximum (95) is above 92.5, so it is an outlier.
- Final answer: Q1 = 30, median = 45, Q3 = 55 minutes; the maximum value of 95 minutes is an outlier and should be plotted as a separate point, with the whisker drawn only to the highest non-outlier value.
Example 2
A grouped frequency table for the daily step count, in thousands, of 130 participants in a fitness challenge is: 20-30, frequency 15; 30-40, frequency 35; 40-50, frequency 50; 50-60, frequency 30. A separate additional fictional observation of 2 thousand steps is not included in this table. (a) Estimate Q1, the median and Q3 for the original 130 observations. (b) Calculate the IQR and the lower outlier boundary. (c) Determine whether the additional observation would be an outlier when compared with the boundaries estimated from the original 130 observations.
- Using only the original 130 observations, n = 130, so Q1 is at position 130/4 = 32.5, the median at 130/2 = 65, and Q3 at 3x130/4 = 97.5.
- Cumulative frequencies are 15, 50, 100, 130 at the class boundaries 30, 40, 50, 60.
- Q1 (32.5) falls in the class 30-40 (cumulative frequency 15 to 50): Q1 = 30 + (32.5-15)/35 x 10 = 35.
- The median (65) and Q3 (97.5) both fall in the class 40-50 (cumulative frequency 50 to 100): median = 40 + (65-50)/50 x 10 = 43; Q3 = 40 + (97.5-50)/50 x 10 = 49.5.
- IQR = 49.5 - 35 = 14.5. Lower outlier boundary = 35 - 1.5 x 14.5 = 13.25.
- The additional fictional observation of 2 (thousand steps) is below 13.25, so it would be an outlier against the lower boundary estimated from the original 130 observations.
- Final answer: Q1=35, median=43, Q3=49.5 (thousand steps) for the original 130 observations; the additional observation of 2 thousand steps would be an outlier against the lower boundary estimated from the original 130 observations.
Practice questions
Q1[2 marks]A data set has Q1 = 12 and Q3 = 20. Calculate the IQR and the upper outlier boundary.Show answer
Answer: IQR = 8; upper boundary = 20 + 1.5 x 8 = 32
Q2[3 marks]A data set has Q1 = 20 and Q3 = 32. Is a value of 55 an outlier? Use the 1.5 x IQR rule.Show answer
Answer: Yes; IQR = 12, upper boundary = 32 + 1.5 x 12 = 50, and 55 is greater than 50
Q3[3 marks]A data set has Q1 = 15 and Q3 = 45. Calculate both outlier boundaries.Show answer
Answer: Lower boundary = 15 - 1.5 x 30 = -30; upper boundary = 45 + 1.5 x 30 = 90
Q4[3 marks]A cumulative frequency table gives Q1 = 18, median = 25, Q3 = 34 for the ages of 60 people at a conference. Calculate the IQR and state the upper outlier boundary.Show answer
Answer: IQR = 34 - 18 = 16; upper boundary = 34 + 1.5 x 16 = 58
Q5[2 marks]Using the data in the previous question, a delegate aged 65 attends. Is this delegate's age an outlier? Explain.Show answer
Answer: Yes; 65 is greater than the upper boundary of 58
Q6[4 marks]A cumulative frequency graph for 100 test scores gives Q1 = 40, median = 58, Q3 = 70, minimum = 5, maximum = 98. Determine which of the minimum and maximum should be plotted as individual outliers.Show answer
Answer: Neither; IQR = 30, boundaries are -5 and 115, and both 5 and 98 lie within this range, so the whiskers extend directly to 5 and 98
Exam-style questions
Written in the style of a GCSE Statistics exam paper, with a full mark scheme.
Exam tips
- State n/4, n/2 and 3n/4 explicitly for Q1, median and Q3 before reading a cumulative frequency table or graph, and double-check you have not mixed up which position belongs to which quartile.
- Always calculate and check both outlier boundaries against the minimum and the maximum, even when one direction seems obviously fine - a data set can have an outlier at either end, both, or neither.
- When drawing or describing a box plot with an outlier, the whisker stops at the most extreme non-outlier value; the outlier itself is marked as a separate point beyond the whisker.
Q1[3 marks]A data set has Q1 = 24 and Q3 = 40. Calculate the IQR and both outlier boundaries.Show mark scheme
Tick each line you got.
Nothing ticked yet - 3 available
Q2[4 marks]The masses, in kg, of 50 parcels have quartiles Q1 = 3.2 kg and Q3 = 7.6 kg. The heaviest parcel has a mass of 15 kg. (a) Calculate the IQR and the upper outlier boundary. (b) Determine whether the heaviest parcel is an outlier.Show mark scheme
Tick each line you got.
Nothing ticked yet - 4 available
Q3[5 marks]A cumulative frequency table for the times, in minutes, of 120 runners gives Q1 = 45, median = 55, Q3 = 65. The slowest runner finished in 140 minutes. (a) Calculate the IQR. (b) Calculate the upper outlier boundary. (c) Determine whether the slowest runner should be shown as an outlier, and explain how their result should be plotted.Show mark scheme
Tick each line you got.
Nothing ticked yet - 5 available
See real GCSE Statistics past-paper questions, with official mark schemes
Free printable worksheet
Want more practice on paper? Download the Box Plots from Cumulative Frequency and Outliers worksheet pack - 29 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 15 of GCSE Statistics Higher Essentials 1, the whole course as one free printable PDF. Its worksheet is also chapter 8 of GCSE Statistics Higher Topic Workbook 2 and chapter 15 of GCSE Statistics Higher 10-Minute Tests 1, free printable practice books.
Other versions of this worksheet: