Revision Library
Choose a subject
Menu
Maths
Need a new topic?
Missing a topic, found a bug, or want something added?
A Level Maths · Topic guide

Statistics: Data Presentation and Interpretation Depth

In A-level Statistics, Data Presentation Depth extends the core measures of location, spread and correlation to the settings that catch students out under exam pressure: reading a histogram where the class widths are not equal (so height alone does not represent frequency), linearly coding a data set to simplify a mean or standard deviation calculation and then reversing the coding, and describing skewness by comparing the mean and the median. The examiner is testing whether a student knows that a histogram's AREA, not its height, represents frequency, can correctly transform a mean and a standard deviation under a coding, and can justify a description of skew rather than just naming it.

A LevelStatisticsEdexcelAQAOCRWJECCCEA

Before you start

Make sure you're comfortable with these topics first:

Method

  1. Decide what the question needs. A histogram question needs frequency density = frequency / class width, remembering that AREA represents frequency. A coding question needs the given transformation (e.g. y = (x-a)/b) applied to, or reversed from, the mean and standard deviation. A skewness question needs a comparison of the mean and the median (or the quartiles).
  2. To read a histogram, use frequency = frequency density x class width for each bar. If one class's frequency (or frequency density) is unknown, use a given total frequency and subtract the known classes' frequencies to find it, then divide by that class's width.
  3. To estimate the median, a quartile, or a frequency for a range that does not align with the class boundaries, use linear interpolation: assume the data is spread evenly across the relevant class, and take the appropriate proportion of that class's width (for a median or quartile) or of its frequency (for an estimated count within part of a class).
  4. For coded data with y = (x-a)/b: mean(y) = (mean(x) - a) / b, and standard deviation(y) = standard deviation(x) / b (subtracting the constant a does not change the spread, only dividing by b does). Rearrange either way, depending on which mean or standard deviation the question gives you.
  5. To describe skewness, compare the mean and the median. If mean > median, the data is positively skewed (a longer tail of unusually high values pulls the mean up); if mean < median, the data is negatively skewed (a longer tail of unusually low values pulls the mean down); if mean is approximately equal to median, the data is roughly symmetrical.
  6. Always finish an interpretation question in the words of the context given (what a difference in spread, or a skew, actually means for these particular data), rather than leaving a bare mathematical statement.

Common mistakes

  • MistakeChanging the standard deviation by the constant a as well as by the multiplier when decoding y = (x - a)/b.

    InsteadSubtracting a constant slides every value by the same amount and leaves the spread unchanged. Only the divisor b rescales the standard deviation: SD(x) = b x SD(y). The mean is decoded in full: mean(x) = b x mean(y) + a.

  • MistakeInterpolating a median or quartile by dividing by the class width instead of the class frequency.

    InsteadThe fraction of the way through the class is (number of values still needed)/(frequency of that class). Multiply that fraction by the class width and add the result to the lower boundary.

  • MistakeGiving a negative standard deviation when the coding has a negative multiplier, such as y = (a - x)/b.

    InsteadA standard deviation is never negative, so use the modulus of the multiplier: SD(x) = |b| x SD(y). The mean does keep the sign: mean(x) = a - b x mean(y).

Worked examples

Example 1

A histogram represents the time, in minutes, spent by 90 customers in a shop, with these class widths and frequency densities: 0 to 10 minutes, frequency density 1.2; 10 to 20 minutes, frequency density 3.0; 20 to 40 minutes, frequency density 1.4; 40 to 70 minutes, frequency density d (unknown). Given that 90 customers were surveyed in total, find the value of d, and hence find the number of customers who spent at least 40 minutes in the shop.

  1. Recall that, in a histogram, frequency = frequency density x class width for each bar.
  2. Find the frequency of each known class: 0-10 minutes: 1.2 x 10 = 12. 10-20 minutes: 3.0 x 10 = 30. 20-40 minutes: 1.4 x 20 = 28.
  3. Sum the known frequencies: 12 + 30 + 28 = 70.
  4. Since the total is 90, the unknown (40-70 minute) class has frequency 90 - 70 = 20.
  5. This class has width 70 - 40 = 30, so d = 20/30 = 2/3 (about 0.67).
  6. Final answer: d = 2/3, and 20 customers spent at least 40 minutes in the shop.

Example 2

The masses, x kg, of 12 boxes are coded using y = (x - 50)/5. The coded data give sum(y) = 24 and sum(y^2) = 180. (a) Find the mean and standard deviation of x. (b) Given that the median of x is 56 kg, describe the skewness of the data, giving a reason.

  1. Mean of y = 24/12 = 2.
  2. Variance of y = 180/12 - 2^2 = 15 - 4 = 11, so SD(y) = sqrt(11) = 3.317.
  3. Decode the mean. From y = (x - 50)/5, x = 5y + 50, so mean(x) = 5(2) + 50 = 60 kg.
  4. Decode the standard deviation. Only the multiplier matters: SD(x) = 5 x sqrt(11) = 16.6 kg (3 s.f.).
  5. The mean (60) is greater than the median (56), so the data have positive skew: a few unusually heavy boxes pull the mean above the median.
  6. Final answer: mean 60 kg, standard deviation 16.6 kg, positive skew.

Practice questions

Q1[1 mark]A histogram bar represents a class of width 5 and is drawn with frequency density 4. State the frequency represented by this bar.Show answer

Answer: Frequency = frequency density x class width = 4 x 5 = 20.

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q2[2 marks]A data set of exam marks, x, is coded using y = (x-40)/2. Given that the mean of y is 12.5, find the mean of x.Show answer

Answer: mean(x) = 2 x mean(y) + 40 = 2(12.5) + 40 = 65.

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q3[1 mark]Using the same coding y = (x-40)/2, given that the standard deviation of y is 3, find the standard deviation of x.Show answer

Answer: standard deviation(x) = 2 x standard deviation(y) = 2(3) = 6.

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q4[2 marks]A data set has mean 45 and median 52. State, with a reason, the type of skew shown.Show answer

Answer: Negative skew, since the mean (45) is lower than the median (52) - a tail of unusually low values is pulling the mean down below the median.

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q5[3 marks]A histogram represents the mass, in kg, of parcels at a depot. The class 10 to 15 kg contains 18 parcels and is drawn with frequency density 3.6. Verify this frequency density is consistent with the class width, and state the height that the bar for a different class, of width 8 kg containing 24 parcels, should be drawn at.Show answer

Answer: 18/5 = 3.6, consistent with the given frequency density. The second bar should be drawn at frequency density 24/8 = 3.

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q6[3 marks]The times, in seconds, taken by 40 students to complete a puzzle are grouped: 0-20 seconds (8 students), 20-30 seconds (17 students), 30-50 seconds (15 students). Use linear interpolation to estimate the median time.Show answer

Answer: The median (20th value) lies in the 20-30 class, since 8 students are below it and 8+17=25 are below the next boundary. Median = 20 + ((20-8)/17) x 10 = 27.1 seconds (3 s.f.).

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q7[2 marks]Explain why, on a histogram with unequal class widths, you cannot compare two classes' frequencies just by comparing the heights of their bars.Show answer

Answer: Frequency is represented by the AREA of a bar (frequency density x class width), not by its height alone. Two classes with different widths need different heights to represent the same frequency, so height alone is only directly comparable when every class has the same width.

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.

Exam-style questions

Written in the style of a A Level Maths exam paper, with a full mark scheme.

Exam tips

  • For a histogram question, build a small table with rows for class width, frequency density and frequency, and check its total against the stated number of values.
  • Decode a coded value by undoing the operations in reverse order: first undo the division or multiplication, then undo the addition or subtraction.
  • After interpolating, check that the estimate lies inside the class you used. If it does not, the class or the cumulative frequency has been misread.
Q1[8 marks]A histogram summarises the distance travelled to work, in km, by 120 office workers, with these class widths and frequency densities: 0-5 km, frequency density 4.4; 5-10 km, frequency density 9.2; 10-20 km, frequency density 2.9; 20-40 km, frequency density h. (a) Find the frequency for each of the first three classes. (3) (b) Given that 120 workers were surveyed in total, find the value of h. (2) (c) Using linear interpolation, estimate the median distance travelled, giving your answer to 3 significant figures. (3)Show mark scheme

Tick each line you got.

Nothing ticked yet - 8 available

Got it right?
Q2[5 marks]The times, in seconds, taken by a group of athletes to run 100 m are coded using y = 10(x-9), giving mean(y) = 8.5 and standard deviation(y) = 4. (a) Find the mean and standard deviation of the original times, x. (3) (b) Given that the median of the original times is 9.65 seconds, determine, with a reason, the type of skewness shown by the data. (2)Show mark scheme

Tick each line you got.

Nothing ticked yet - 5 available

Got it right?
Q3[4 marks]A histogram represents the age, in years, of 90 members of a gym, with these class widths and frequency densities: 16-25 years, frequency density 2; 25-30 years, frequency density 9; 30-50 years, frequency density 1.35. (a) Show that these frequency densities are consistent with a total of 90 members. (2) (b) Assuming ages are spread uniformly within the 25-30 class, estimate the number of members aged between 27 and 30. (2)Show mark scheme

Tick each line you got.

Nothing ticked yet - 4 available

Got it right?

See real A Level Maths 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:

Free printable worksheet

Want more practice on paper? Download the Statistics: Data Presentation and Interpretation Depth worksheet pack - 9 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 7 of A Level Maths Statistics Essentials, the whole course as one free printable PDF. Its worksheet is also chapter 7 of A Level Maths Statistics Topic Workbook and chapter 7 of A Level Maths 10-Minute Tests 2, free printable practice books.

Other versions of this worksheet:

Keep going

Not quite what you needed?

Tell us what is missing on Statistics: Data Presentation and Interpretation Depth, or which topic to write up next.

Build a full practice pack.