Statistics: Data Presentation and Interpretation
Data presentation and interpretation covers the methods used to summarise, display and describe a set of data, including measures of location and spread, correlation, and diagrams such as histograms and box plots. A Level Statistics also covers identifying outliers, coding data, and interpreting scatter diagrams and box plots in context.
Method
- Calculate the mean using (sum of the values) / n, and for grouped data use the midpoint of each class in place of the actual values.
- Calculate the standard deviation using sqrt[(sum of x^2)/n - mean^2], using the midpoint of each class for grouped data.
- To find the median and quartiles from a list, use their position in the ordered data; for grouped data, use linear interpolation within the class that contains the median or quartile.
- Identify outliers using a stated rule, e.g. more than 2 standard deviations from the mean, or more than 1.5 x IQR beyond the nearer quartile, and check each value against the calculated boundary.
- Use a scatter diagram to describe correlation as positive, negative or (approximately) zero, and comment on how an unusual point would affect the product moment correlation coefficient.
- When comparing two data sets (e.g. using box plots), compare a measure of location (mean or median) and a measure of spread (range or IQR), always writing the comparison in context.
Common mistakes
MistakeGiving sum(x^2)/n - mean^2 as the standard deviation, so the variance is reported instead.
InsteadThat expression is the variance. Take its square root to get the standard deviation. The standard deviation is in the units of the data (for example kg), while the variance is in squared units.
MistakeDeleting an outlier from the data simply because it looks unusual.
InsteadAn outlier is a value flagged by a stated rule, not a value to throw away. Look for a reason in the context, such as a recording error. Only if there is one, remove it, and then recalculate every statistic from the remaining data.
MistakeSaying that a strong correlation shows that one variable causes the other.
InsteadCorrelation describes how two variables vary together. Describe the pattern in context ('as ... increases, ... tends to increase') and, if asked, say that a strong correlation does not by itself show cause.
MistakeUsing the upper class boundary instead of the class midpoint when estimating a mean from grouped data.
InsteadThe midpoint stands in for values assumed to be spread evenly through the class. For each class find (lower boundary + upper boundary)/2, multiply by the frequency, then divide the total by the number of values.
Worked examples
Example 1
The times, in minutes, taken by 8 runners to complete a 5 km route are: 28, 31, 26, 35, 30, 27, 33, 29. (a) Calculate the mean time. (b) Calculate the standard deviation of these times. (c) A ninth runner joins with a time of 50 minutes, a clear outlier. Without recalculating, state and justify the effect on the mean and standard deviation.
- Sum of the 8 times = 28+31+26+35+30+27+33+29 = 239. Mean = 239/8 = 29.875 minutes.
- Sum of squares = 28^2+31^2+26^2+35^2+30^2+27^2+33^2+29^2 = 784+961+676+1225+900+729+1089+841 = 7205.
- Variance = 7205/8 - 29.875^2 = 900.625 - 892.515625 = 8.109375. Standard deviation = sqrt(8.109375) = 2.848 (3dp).
- Adding 50 (well above the current mean of 29.875) would increase the mean, since it pulls the average up.
- The standard deviation would also increase, since 50 is a long way from the mean and adds a large deviation, increasing the overall spread.
Example 2
The masses, in grams, of 15 parcels have sum(x) = 300 and sum(x^2) = 6420. (a) Find the mean and the standard deviation. (b) The largest mass is 32 g. Using the rule that a value is an outlier if it is more than 2 standard deviations above the mean, show that 32 g is an outlier. (c) The 32 g value was a recording error and is removed. Find the mean and standard deviation of the remaining 14 masses.
- Mean = 300/15 = 20 g.
- Variance = 6420/15 - 20^2 = 428 - 400 = 28, so the standard deviation = sqrt(28) = 5.29 g (3 s.f.).
- Upper boundary = 20 + 2(5.2915) = 30.58 g. Since 32 > 30.58, the value 32 g is an outlier.
- Remove it: n = 14, sum(x) = 300 - 32 = 268 and sum(x^2) = 6420 - 32^2 = 6420 - 1024 = 5396.
- New mean = 268/14 = 19.1 g (3 s.f.).
- New variance = 5396/14 - (268/14)^2 = 385.43 - 366.45 = 18.98 (2 d.p.), so the new standard deviation = 4.36 g (3 s.f.).
- Final answer: originally mean 20 g and standard deviation 5.29 g; after removing 32 g, mean 19.1 g and standard deviation 4.36 g.
Example 3
In a fictional model, ten machine cycles have durations t seconds recorded only in this grouped frequency table: 2 <= t < 6, frequency 3; 6 <= t < 12, frequency 5; 12 <= t < 14, frequency 2. Estimate the mean duration using class midpoints and explain the assumption. Give a possible set of durations with a different mean but the same grouped table, to show why the raw-data mean cannot be found exactly.
- Find the class midpoints: (2 + 6)/2 = 4, (6 + 12)/2 = 9 and (12 + 14)/2 = 13 seconds. Use the midpoint of each class even though the class widths differ.
- Multiply each midpoint by its frequency: 3 x 4 = 12, 5 x 9 = 45 and 2 x 13 = 26. The estimated total duration is 12 + 45 + 26 = 83 seconds.
- The total frequency is 3 + 5 + 2 = 10. Divide the estimated total by the total frequency: estimated mean = 83/10 = 8.3 seconds.
- This treats each class mean as its midpoint. An even spread within each class would support that assumption, but the grouped table does not show the actual positions of the durations within the classes.
- For a different possible raw data set, take three durations of 2 seconds, five of 6 seconds and two of 12 seconds. These lower boundaries are included in their respective classes. The total is 3 x 2 + 5 x 6 + 2 x 12 = 60 seconds, giving a mean of 6 seconds with the same grouped table.
- Alternatively, putting every duration at its class midpoint gives the same frequencies and an exact raw-data mean of 8.3 seconds. Since the table allows both sets, it does not determine the exact raw-data mean.
- Final answer: the estimated mean duration is 8.3 seconds. It is an estimate because the class midpoints replace unknown durations; the exact raw-data mean cannot be recovered from the grouped frequencies alone.
Practice questions
Q1[2 marks]Calculate the mean of the data set: 4, 7, 9, 12, 13.Show answer
Answer: 9 (sum = 45, divided by 5).
Q2[1 mark]The lower quartile of a data set is 12 and the upper quartile is 20. Calculate the interquartile range.Show answer
Answer: 8 (20 - 12).
Q3[1 mark]In a scatter diagram, taller people tend to have larger shoe sizes. State the type of correlation shown between height and shoe size.Show answer
Answer: Positive correlation.
Q4[3 marks]For 6 values, sum of x = 90 and sum of x^2 = 1400. Calculate the standard deviation.Show answer
Answer: awrt 2.89 (sqrt(1400/6 - 15^2) = sqrt(8.33)).
Q5[3 marks]A data set has median 40, Q1 = 30 and Q3 = 52. Determine whether the value 90 is an outlier, using the rule that a value is an outlier if it lies more than 1.5 x IQR beyond the nearer quartile.Show answer
Answer: Yes; IQR = 22, so the upper boundary is 52 + 1.5(22) = 85, and 90 > 85.
Q6[3 marks]The heights, in cm, of 40 tomato plants are grouped: 20-30 (6 plants), 30-40 (14 plants), 40-50 (15 plants), 50-60 (5 plants). Using the midpoint of each class, calculate an estimate of the mean height.Show answer
Answer: 39.75 cm (sum of frequency x midpoint = 1590, divided by 40).
Exam-style questions
Written in the style of a A Level Maths exam paper, with a full mark scheme.
Exam tips
- Write the outlier rule you are using, and the boundary it gives, before comparing any data value with it.
- When comparing two data sets, write one sentence about a measure of location and one about a measure of spread, each naming the variable in context.
- To find a standard deviation from sums, set out n, the sum of x, the sum of x^2 and the mean on separate lines so that an arithmetic slip can be traced.
Q1[4 marks]The mass, in kg, of 10 sacks of potatoes are: 24, 26, 22, 29, 25, 23, 28, 27, 26, 30. (a) Calculate the mean mass. (2) (b) Calculate the standard deviation of the masses. (2)Show mark scheme
Tick each line you got.
Nothing ticked yet - 4 available
Q2[5 marks]The weekly hours worked by 11 part-time staff, listed in ascending order, are: 10, 12, 14, 15, 17, 18, 19, 21, 23, 25, 48. (a) Find the median, the lower quartile (Q1) and the upper quartile (Q3). (3) (b) Show that 48 hours is an outlier, using the rule that a value is an outlier if it lies more than 1.5 x IQR beyond the nearer quartile. (2)Show mark scheme
Tick each line you got.
Nothing ticked yet - 5 available
Q3[6 marks]Two classes, C and D, sat the same physics test out of 60 marks. Box plots of their results gave the following five-figure summaries. Class C: minimum = 15, Q1 = 24, median = 33, Q3 = 44, maximum = 52. Class D: minimum = 20, Q1 = 30, median = 34, Q3 = 37, maximum = 40. (a) Compare the medians and the interquartile ranges of the two classes, in the context of the test. (3) (b) Using the quartiles, comment on the skewness of each class's distribution of marks. (3)Show mark scheme
Tick each line you got.
Nothing ticked yet - 6 available
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:
- OCR AS Level Maths past papers: 13 questions across 7 papers, latest tagged June 2024
- AQA A Level Maths past papers: 10 questions across 6 papers, latest tagged June 2023
- OCR A Level Maths past papers: 6 questions across 5 papers, latest tagged June 2023
- WJEC A Level Maths past papers: 6 questions across 3 papers, latest tagged Summer 2022
Free printable worksheet
Want more practice on paper? Download the Statistics: Data Presentation and Interpretation 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 2 of A Level Maths Statistics Essentials, the whole course as one free printable PDF. Its worksheet is also chapter 2 of A Level Maths Statistics Topic Workbook and chapter 2 of A Level Maths 10-Minute Tests 2, free printable practice books.
Other versions of this worksheet: