Statistics
By the end of this chapter you will be able to
- Tell categorical from numerical data, and discrete from continuous data
- Read and draw frequency tables, bar charts, pictograms and line graphs
- Find the mean, median, mode and range of a list, and of a frequency table
- Estimate the mean of grouped data using the midpoints of the groups
- Describe the correlation in a scatter graph, and use a line of best fit to estimate a value
- Compare two sets of data using an average and the spread
You should already know
- Ordering numbers, tally charts and frequency tables (Year 6, Chapter 13)
- Mean as sharing equally, and the fraction and percentage ideas from Chapter 2
- Coordinates and graphs (Chapter 7)
Where this leads
- Cumulative frequency, box plots and histograms in Year 8
- Standard deviation and more complex statistical models in Years 8 and 9
National Curriculum for England, Key Stage 3 mathematics, Year 7. Content: S1 describe, interpret and compare distributions of one variable with suitable graphs, and measures of average and spread (mean, median, mode, range), S2 construct and interpret tables, charts and diagrams for categorical data, and bar and line charts for numerical data, ungrouped or grouped, S3 describe simple relationships between two variables (bivariate data) and illustrate them with a scatter graph.
Exercise P Do you remember?
Non-calculatorMethod. Divide the total into 3 equal parts.
- Read the data. Write down the values before working out the statistic.15 ÷ 3 = 5
- Divide. Share 15 into 3 equal groups.15 ÷ 3 = 5
- Write the answer. Give the answer with its unit.5
Check. 5 × 3 = 15. ✓
Watch out. Check by multiplying back.
Method. Compare the numbers and list them from the smallest.
- Read the data. Write down the values before working out the statistic.1, 4, 7, 9
- Order. The smallest is 1, then 4, then 7, then 9.1, 4, 7, 9
- Write the answer. Give the answer with its unit.1, 4, 7, 9
Check. Each number is bigger than the one before. ✓
Watch out. Start with the smallest.
Method. Add the three numbers.
- Read the data. Write down the values before working out the statistic.6 + 8 + 10 = 24
- Add. Add all three values.6 + 8 + 10 = 24
- Write the answer. Give the answer with its unit.24
Check. 24 ÷ 3 = 8, the average. ✓
Watch out. Add all the values.
Method. Put the numbers in order and find the middle one.
- Order. The numbers are already in order: 3, 5, 9.3, 5, 9
- Middle. The middle of three numbers is the second.5
- Write the answer. Give the answer with its unit.5
Check. One number is below 5 and one above. ✓
Watch out. The middle is the median.
Method. Add the numbers.
- Read the data. Write down the values before working out the statistic.7 + 9 = 16, and 16 + 4 = 20
- Add. Add in any order.7 + 9 = 16, and 16 + 4 = 20
- Write the answer. Give the answer with its unit.20
Check. 20 − 4 = 16. ✓
Watch out. Add in pairs if you like.
Types of data and frequency tables
Categorical data is in groups described by words, such as favourite colour. Numerical data is a number: discrete numerical data is counted in whole steps (such as shoe size), and continuous numerical data is measured (such as height in cm).
A frequency table lists each value (or group) and how many times it occurs. The total frequency is the sum of all the frequencies.
Key ideas
- Categorical: groups described in words, such as colour or pet.
- Discrete numerical: counted in whole numbers, such as the number of goals.
- Continuous numerical: measured, such as height or time.
- Total frequency = the sum of all the frequencies.
Method. Count how many pupils have each size.
- Count the 6s. Three pupils have size 6.6: 3
- Count the 7s and 8s. Two pupils have size 7 and one has size 8.7: 2, 8: 1
- Write the answer. Give the answer with its unit.Size 6: 3, size 7: 2, size 8: 1
Check. 3 + 2 + 1 = 6 pupils. ✓
Watch out. Check the total of the frequencies is 6.
Method. Height is measured, not counted.
- Read the data. Write down the values before working out the statistic.measured
- Decide the type. Height is a number that can take any value in a range.measured
- Write the answer. Give the answer with its unit.numerical and continuous
Check. Height can be 150.5 cm, so it is continuous. ✓
Watch out. Measured quantities are continuous.
Method. The number of brothers is counted.
- Read the data. Write down the values before working out the statistic.counted
- Decide the type. It is a count of whole people, in steps of 1.counted
- Write the answer. Give the answer with its unit.numerical and discrete
Check. You cannot have 2.5 brothers. ✓
Watch out. Counts are discrete.
Watch out
Watch out: shoe size is not continuous, because sizes go up in steps (such as 6, 6.5, 7). A discrete quantity has gaps between values.
Exam tip
Grown-up tip. Ask the pupil to make a tally of the colours of the cars passing the window for two minutes.
Exercise 13A Data types and frequency tables
Non-calculatorMethod. Colours are words.
- Read the data. Write down the values before working out the statistic.categorical
- Decide. Colours are described by words, not counted.categorical
- Write the answer. Give the answer with its unit.categorical
Check. Words describe the groups. ✓
Watch out. Words are categorical.
Method. It is counted.
- Read the data. Write down the values before working out the statistic.discrete
- Decide. Counts go up in whole numbers.discrete
- Write the answer. Give the answer with its unit.discrete
Check. You cannot have half a brother. ✓
Watch out. Counts are discrete.
Method. It is measured.
- Read the data. Write down the values before working out the statistic.continuous
- Decide. Heights can take any value.continuous
- Write the answer. Give the answer with its unit.continuous
Check. Heights can be 150.5 cm. ✓
Watch out. Measurements are continuous.
Method. Count the 6s.
- Read the data. Write down the values before working out the statistic.3
- Count. Three values are 6.3
- Write the answer. Give the answer with its unit.3
Check. 3 + 2 + 1 = 6 pupils. ✓
Watch out. Count each value.
Method. Add the frequencies.
- Read the data. Write down the values before working out the statistic.20
- Add. 4 + 7 + 3 + 6.20
- Write the answer. Give the answer with its unit.20
Check. 20 − 6 = 14, and 14 + 6 = 20. ✓
Watch out. Add all the frequencies.
Method. Tally the A votes.
- Read the data. Write down the values before working out the statistic.4
- Count. A appears at positions 1, 3, 6 and 7.4
- Write the answer. Give the answer with its unit.4
Check. The other votes: B 2, C 1, total 7. ✓
Watch out. Use a tally.
Method. Total minus the known frequencies.
- Add the known. 5 + 4 = 9.9
- Subtract. 14 − 9.5
- Write the answer. Give the answer with its unit.5
Check. 5 + 5 + 4 = 14. ✓
Watch out. Subtract the known frequencies from the total.
Method. The biggest frequency.
- Read the data. Write down the values before working out the statistic.blue
- Compare. 8 is the biggest.blue
- Write the answer. Give the answer with its unit.blue
Check. 8 > 5 and 8 > 3. ✓
Watch out. Look for the largest number.
Method. Total minus apples.
- Read the data. Write down the values before working out the statistic.18
- Subtract. 30 − 12.18
- Write the answer. Give the answer with its unit.18
Check. 12 + 10 + 8 = 30. ✓
Watch out. Subtract the apples from the total.
Method. Ages are counted in whole years.
- Read the data. Write down the values before working out the statistic.discrete
- Decide. Whole numbers of years.discrete
- Write the answer. Give the answer with its unit.numerical, discrete
Check. Age goes up in whole years. ✓
Watch out. Counted in whole years.
Method. Mass is measured.
- Read the data. Write down the values before working out the statistic.continuous
- Decide. Mass can take any value.continuous
- Write the answer. Give the answer with its unit.numerical, continuous
Check. Mass can be 2.35 kg. ✓
Watch out. Measured quantities are continuous.
Method. Pets are described by words.
- Read the data. Write down the values before working out the statistic.categorical
- Decide. The answers are types of pet.categorical
- Write the answer. Give the answer with its unit.categorical
Check. Words describe the groups. ✓
Watch out. Words are categorical.
Method. Think about the steps between the values.
- Look at the steps. Sizes go up in fixed steps.steps
- Decide. A discrete quantity has gaps between its values.discrete
- Write the answer. Give the answer with its unit.Shoe size is discrete
Check. It has gaps between possible values. ✓
Watch out. A continuous value can take any value in a range.
Bar charts, pictograms and line graphs
A pictogram uses a picture to stand for a number, and a key says what each picture means. A line graph joins points over time, so it shows change.
Key ideas
- A bar chart: the bars start at 0 and have equal widths and gaps.
- A pictogram: check the key to find the value of one picture; a half picture is half the key value.
- A line graph shows change over time: read values across, then up or down.
- Read the axis scale carefully: the marks may count in 2s, 5s or 10s.
Method. Multiply the number of symbols by the key.
- Read the key. One symbol is 5 pupils.1 symbol = 5 pupils
- Multiply. 6 symbols are 6 × 5.30
- Write the answer. Give the answer with its unit.30 pupils
Check. 30 ÷ 5 = 6 symbols. ✓
Watch out. Use the key, not the number of symbols alone.
Method. Add the three bars.
- Read the data. Write down the values before working out the statistic.12 + 9 + 15 = 36
- Add. Add the three values from the chart.12 + 9 + 15 = 36
- Write the answer. Give the answer with its unit.36 books
Check. 36 ÷ 3 = 12. ✓
Watch out. Add each bar once.
Method. Subtract the earlier value from the later value.
- Read the data. Write down the values before working out the statistic.14 − 8 = 6
- Find the change. The temperature went up.14 − 8 = 6
- Write the answer. Give the answer with its unit.6°C rise
Check. 8 + 6 = 14. ✓
Watch out. Subtract the earlier from the later.
Watch out
Watch out: a bar chart does not have a value of "half a pupil". With a key of 5, a half symbol means 2.5 pupils; check the key before you count.
Exam tip
Grown-up tip. Ask the pupil to read the key first, and to say the value of one picture aloud before counting.
Exercise 13B Bar charts, pictograms and line graphs
Non-calculatorMethod. Multiply.
- Read the data. Write down the values before working out the statistic.30
- Multiply. 6 × 5.30
- Write the answer. Give the answer with its unit.30 pupils
Check. 30 ÷ 5 = 6. ✓
Watch out. Use the key.
Method. Half a symbol is half the key value.
- Read the data. Write down the values before working out the statistic.14
- Find the value. 3 × 4 = 12 and a half is 2.14
- Write the answer. Give the answer with its unit.14 pupils
Check. 14 ÷ 4 = 3.5. ✓
Watch out. Half a symbol is half the key.
Method. Add the three bars.
- Read the data. Write down the values before working out the statistic.36
- Add. 12 + 9 + 15.36
- Write the answer. Give the answer with its unit.36 books
Check. 36 ÷ 3 = 12. ✓
Watch out. Add all three.
Method. Find the tallest bar.
- Read the data. Write down the values before working out the statistic.Wednesday
- Compare. Wednesday has 15, the biggest value.Wednesday
- Write the answer. Give the answer with its unit.Wednesday
Check. 15 is more than 12 and 9. ✓
Watch out. Look for the biggest value.
Method. Subtract.
- Read the data. Write down the values before working out the statistic.6
- Subtract. 15 − 9.6
- Write the answer. Give the answer with its unit.6 books
Check. 9 + 6 = 15. ✓
Watch out. Subtract the smaller from the larger.
Method. Subtract the earlier from the later.
- Read the data. Write down the values before working out the statistic.6
- Subtract. 14 − 8.6
- Write the answer. Give the answer with its unit.6°C
Check. 8 + 6 = 14. ✓
Watch out. Subtract.
Method. One bar for each category.
- Read the data. Write down the values before working out the statistic.4
- Count. One bar per category.4
- Write the answer. Give the answer with its unit.4 bars
Check. 4 categories, 4 bars. ✓
Watch out. One bar each.
Method. Divide the books by the key.
- Read the data. Write down the values before working out the statistic.7.5
- Divide. 75 ÷ 10 = 7.5.7.5
- Write the answer. Give the answer with its unit.7 and a half symbols
Check. 7 × 10 = 70, and 5 more is 75. ✓
Watch out. Half a symbol is half the key.
Method. Subtract the earlier value.
- Read the data. Write down the values before working out the statistic.25
- Subtract. 65 − 40.25
- Write the answer. Give the answer with its unit.25
Check. 40 + 25 = 65. ✓
Watch out. Subtract.
Method. Add the values.
- Read the data. Write down the values before working out the statistic.15
- Add. 5 + 8 + 2.15
- Write the answer. Give the answer with its unit.15
Check. 15 − 8 = 7 = 5 + 2. ✓
Watch out. Add them.
Method. Compare the values.
- Read the data. Write down the values before working out the statistic.8
- Compare. 8 is the biggest.8
- Write the answer. Give the answer with its unit.8
Check. 8 > 5 and 8 > 2. ✓
Watch out. Biggest value.
Method. Subtract.
- Read the data. Write down the values before working out the statistic.6
- Subtract. 8 − 2.6
- Write the answer. Give the answer with its unit.6
Check. 2 + 6 = 8. ✓
Watch out. Subtract the smallest from the largest.
Method. Think about what the bar lengths show.
- Look at the bars. The length of a bar shows the size of the value.length
- Compare. If the axis starts at 5, a value of 6 looks many times bigger than 5.misleading
- Write the answer. Give the answer with its unit.Start at 0, so the bar lengths are fair
Check. A bar starting at 0 shows the true ratio. ✓
Watch out. The length must match the value.
Mean, median, mode and range
For an even number of values, the median is the mean of the two middle values.
Key ideas
- Mean = total of the values ÷ the number of values.
- Median = the middle value after sorting (the mean of the two middle values when there are an even number).
- Mode = the value that occurs most often (there can be more than one, or none).
- Range = the biggest value − the smallest value.
Method. Work out each average and spread.
- Mean. Total 3 + 7 + 2 + 8 + 5 = 25, shared by 5.25 ÷ 5 = 5
- Median. In order: 2, 3, 5, 7, 8. The middle is 5.5
- Range. Biggest 8 − smallest 2.8 − 2 = 6
- Write the answer. Give the answer with its unit.mean 5, median 5, range 6
Check. Mean and median are both 5, range 6. ✓
Watch out. Sort before finding the median.
Method. There are four values, so the median is the mean of the two middle values.
- Find the middle two. In order: 2, 4, 6, 8; the middle two are 4 and 6.4 and 6
- Find the mean of these. Add and halve.(4 + 6) ÷ 2 = 5
- Write the answer. Give the answer with its unit.5
Check. The median lies between 4 and 6. ✓
Watch out. Halve the sum of the two middle values.
Method. Count how many times each value occurs.
- Read the data. Write down the values before working out the statistic.3 appears 3 times
- Count the 3s. The value 3 occurs three times, more than any other.3 appears 3 times
- Write the answer. Give the answer with its unit.3
Check. Other values occur once. ✓
Watch out. The mode is the most common value.
Watch out
Watch out: the median needs the values in order first. Taking the median of 8, 3, 5 without sorting gives the wrong answer.
Exam tip
Grown-up tip. Ask the pupil to write the values on cards and move them into order before finding the median.
Exercise 13C Mean, median, mode and range
Non-calculatorMethod. Total and divide.
- Total. 4 + 6 + 8 + 10 = 28.28
- Divide. 28 ÷ 4.7
- Write the answer. Give the answer with its unit.7
Check. 7 × 4 = 28. ✓
Watch out. Divide by the number of values.
Method. Sort the values first.
- Sort. 1, 3, 5, 7, 9.1, 3, 5, 7, 9
- Middle. The middle value is 5.5
- Write the answer. Give the answer with its unit.5
Check. Two values below and two above 5. ✓
Watch out. Sort first.
Method. Two middle values.
- Middle two. 4 and 6.4, 6
- Mean of them. (4 + 6) ÷ 2.5
- Write the answer. Give the answer with its unit.5
Check. Between 4 and 6. ✓
Watch out. Halve the sum.
Method. Count each value.
- Read the data. Write down the values before working out the statistic.3
- Count. 3 occurs three times.3
- Write the answer. Give the answer with its unit.3
Check. It occurs more often than any other. ✓
Watch out. The most common value.
Method. Biggest minus smallest.
- Read the data. Write down the values before working out the statistic.14
- Subtract. 19 − 5.14
- Write the answer. Give the answer with its unit.14
Check. 5 + 14 = 19. ✓
Watch out. Use the biggest and smallest.
Method. Total of the values times frequencies, divided by the total frequency.
- Multiply. 1 × 2 + 2 × 2 + 3 × 1.2 + 4 + 3 = 9
- Divide. The total frequency is 2 + 2 + 1 = 5.9 ÷ 5 = 1.8
- Write the answer. Give the answer with its unit.1.8
Check. 1.8 × 5 = 9. ✓
Watch out. Use the frequencies as multipliers.
Method. The total is 5 × 8 = 40.
- Total. 5 × 8 = 40.40
- Fifth number. Subtract the four known numbers: 6 + 7 + 9 + 10 = 32.40 − 32 = 8
- Write the answer. Give the answer with its unit.8
Check. 6 + 7 + 9 + 10 + 8 = 40. ✓
Watch out. Use the total.
Method. Sort, then find the middle two and the spread.
- Sort. 9, 12, 14, 20.9, 12, 14, 20
- Median. (12 + 14) ÷ 2 = 13.13
- Range. 20 − 9 = 11.11
- Write the answer. Give the answer with its unit.median 13, range 11
Check. Median 13 lies between 12 and 14. ✓
Watch out. Sort first.
Method. Mode: the most common. Median: the middle of seven values.
- Mode. 8 occurs three times.8
- Median. The middle (4th) value of 7 is 7.7
- Write the answer. Give the answer with its unit.mode 8, median 7
Check. Three values below 7 and three above. ✓
Watch out. Count the middle of seven values.
Method. Total and divide.
- Total. 2 + 4 + 9 = 15.15
- Divide. 15 ÷ 3.5
- Write the answer. Give the answer with its unit.5
Check. 5 × 3 = 15. ✓
Watch out. Divide by 3.
Method. Sort, then take the middle.
- Sort. 2, 7, 10.2, 7, 10
- Middle. The middle value is 7.7
- Write the answer. Give the answer with its unit.7
Check. Two values each side. ✓
Watch out. Sort first.
Method. Biggest minus smallest.
- Read the data. Write down the values before working out the statistic.12
- Subtract. 15 − 3.12
- Write the answer. Give the answer with its unit.12
Check. 3 + 12 = 15. ✓
Watch out. Use the extremes.
Method. Total of five = 5 × 60 = 300.
- Total. 5 × 60 = 300.300
- Fifth. The four known scores add to 255, so 300 − 255.45
- Write the answer. Give the answer with its unit.45
Check. 55 + 62 + 68 + 70 + 45 = 300. ✓
Watch out. Use the total.
Method. Compare the mean and the median.
- Mean. (2 + 3 + 4 + 100) ÷ 4 = 109 ÷ 4 = 27.25.27.25
- Median. The middle two are 3 and 4, so the median is 3.5.3.5
- Write the answer. Give the answer with its unit.The median is better, because the outlier does not change it
Check. The mean is pulled up by 100. ✓
Watch out. Outliers affect the mean much more than the median.
Grouped data and the estimated mean
A grouped frequency table shows how many values lie in each group. The modal class is the group with the highest frequency. To estimate the mean: multiply each midpoint by its frequency, add the results, and divide by the total frequency.
| Height (cm) | Frequency |
|---|---|
| 140 ≤ h < 150 | 2 |
| 150 ≤ h < 160 | 5 |
| 160 ≤ h < 170 | 8 |
| 170 ≤ h < 180 | 5 |
Key ideas
- Midpoint of a group = (lower + upper) ÷ 2.
- Estimated mean = (sum of midpoint × frequency) ÷ (total frequency).
- The modal class is the group with the highest frequency.
- Groups use ≤ and <: 150 ≤ h < 160 includes 150 but not 160.
Method. The group with the largest frequency.
- Compare the frequencies. The frequencies are 2, 5, 8 and 5.8 is the biggest
- Name the group. The frequency 8 belongs to 160 ≤ h < 170.160 ≤ h < 170
- Write the answer. Give the answer with its unit.160 ≤ h < 170
Check. 8 is the highest frequency. ✓
Watch out. The modal class has the highest frequency.
Method. Use the midpoints.
- Find the midpoints. 145, 155, 165 and 175.145, 155, 165, 175
- Multiply and add. 2 × 145 + 5 × 155 + 8 × 165 + 5 × 175 = 3260.3260
- Divide by the total frequency. The total frequency is 20.3260 ÷ 20 = 163
- Write the answer. Give the answer with its unit.163 cm
Check. The estimate is close to the middle group. ✓
Watch out. The estimate uses midpoints, not the exact heights.
Method. Add the two ends and halve.
- Add. 20 + 30 = 50.50
- Halve. Midpoint = 50 ÷ 2.25
- Write the answer. Give the answer with its unit.25
Check. 25 is halfway between 20 and 30. ✓
Watch out. Use the midpoint, not the upper end.
Watch out
Watch out: the estimated mean is not always the exact mean. The midpoint assumes each value is in the middle of its group.
Exam tip
Grown-up tip. Ask the pupil to write the midpoint of each group in a column first, then multiply by the frequency in the next column.
Exercise 13D Grouped data
Non-calculatorMethod. Highest frequency.
- Look. The highest frequency is 8.8
- Name the group. That group is 160 ≤ h < 170.160 ≤ h < 170
- Write the answer. Give the answer with its unit.160 ≤ h < 170
Check. 8 is the largest. ✓
Watch out. Look at the frequencies.
Method. Read the frequency.
- Read the data. Write down the values before working out the statistic.5
- Read. The frequency for 150 to 160 is 5.5
- Write the answer. Give the answer with its unit.5
Check. 2 + 5 + 8 + 5 = 20. ✓
Watch out. Read the table.
Method. Add all the frequencies.
- Read the data. Write down the values before working out the statistic.20
- Add. 2 + 5 + 8 + 5.20
- Write the answer. Give the answer with its unit.20
Check. 20 pupils in total. ✓
Watch out. Add the frequencies.
Method. Add the ends and halve.
- Add. 140 + 150 = 290.290
- Halve. 290 ÷ 2.145
- Write the answer. Give the answer with its unit.145 cm
Check. 145 is halfway between 140 and 150. ✓
Watch out. Halve the sum of the ends.
Method. Midpoints times frequencies, divided by 20.
- Multiply and add. 2 × 145 + 5 × 155 + 8 × 165 + 5 × 175 = 3260.3260
- Divide. 3260 ÷ 20.163
- Write the answer. Give the answer with its unit.163 cm
Check. 20 × 163 = 3260. ✓
Watch out. Use the midpoints.
Method. The median is the average of the 10th and 11th values.
- Cumulative frequency. The first two groups have 2, then 7, then 15 pupils.2, 7, 15
- Find the group. The 10th and 11th values are in the third group.160 ≤ h < 170
- Write the answer. Give the answer with its unit.160 ≤ h < 170
Check. 7 pupils are below 160, and 15 are below 170. ✓
Watch out. Use the running total.
Method. The group with the highest frequency.
- Compare. 6 is the highest frequency.6
- Name. That group is 5 to 10.5 to 10
- Write the answer. Give the answer with its unit.5 to 10 books
Check. 4 + 6 + 2 = 12. ✓
Watch out. Look for the highest frequency.
Method. Midpoints times frequencies, divided by the total.
- Multiply and add. 4 × 2.5 + 6 × 7.5 + 2 × 12.5 = 10 + 45 + 25 = 80.80
- Divide. Total frequency 12: 80 ÷ 12 = 6.666..., which is 6.7 to 1 decimal place.6.7
- Write the answer. Give the answer with its unit.6.7 books
Check. 6.7 × 12 = 80.4, close to 80. ✓
Watch out. Give the answer to 1 decimal place.
Method. Add the ends and halve.
- Read the data. Write down the values before working out the statistic.5
- Add and halve. (0 + 10) ÷ 2.5
- Write the answer. Give the answer with its unit.5
Check. 0 + 5 + 5 = 10. ✓
Watch out. Halve the sum.
Method. Add the ends and halve.
- Read the data. Write down the values before working out the statistic.15
- Add and halve. (10 + 20) ÷ 2.15
- Write the answer. Give the answer with its unit.15
Check. 15 is halfway. ✓
Watch out. Halve the sum.
Method. Width = upper end − lower end.
- Read the data. Write down the values before working out the statistic.10
- Subtract. 30 − 20.10
- Write the answer. Give the answer with its unit.10
Check. 20 + 10 = 30. ✓
Watch out. Subtract the ends.
Method. Each group adds 5.
- Read the data. Write down the values before working out the statistic.25 to 30
- Count up. 10 to 15, 15 to 20, 20 to 25, 25 to 30.25 to 30
- Write the answer. Give the answer with its unit.25 to 30
Check. Four groups of width 5 make 20. ✓
Watch out. Each group adds the width.
Method. Think about what the midpoint assumes.
- Look at the midpoint. The midpoint is the middle of the group.middle of group
- Compare. The real values may be spread out, so the mean can differ.may differ
- Write the answer. Give the answer with its unit.The midpoint is only an estimate of each value
Check. The estimate is close, but not exact. ✓
Watch out. An estimate uses the middle of each group.
Scatter graphs and correlation
Positive correlation: as one variable goes up, the other tends to go up. Negative correlation: as one goes up, the other tends to go down. No correlation: no clear pattern. A line of best fit is a straight line that follows the trend, and it can be used to estimate values.
Key ideas
- Scatter graph: each point is one pair of values (x, y).
- Positive correlation: points go up from left to right. Negative: points go down.
- No correlation: the points are scattered with no pattern.
- Correlation does not prove that one variable causes the other.
Method. Look at the direction of the points.
- Read the data. Write down the values before working out the statistic.up from left to right
- Look. As the hours increase, the marks increase.up from left to right
- Write the answer. Give the answer with its unit.positive correlation
Check. More revision goes with higher marks. ✓
Watch out. Up from left to right is positive.
Method. Look at the direction of the points.
- Read the data. Write down the values before working out the statistic.down from left to right
- Look. As the temperature rises, fewer hot drinks are sold.down from left to right
- Write the answer. Give the answer with its unit.negative correlation
Check. The points go down from left to right. ✓
Watch out. Down from left to right is negative.
Method. Find the gradient, then use the line.
- Find the gradient. Gradient = (70 − 40) ÷ (8 − 2) = 30 ÷ 6.5
- Use the line. From (2, 40), go 4 across: 40 + 5 × 4.60
- Write the answer. Give the answer with its unit.60
Check. The line passes through (6, 60). ✓
Watch out. Use the gradient from the two points.
Watch out
Watch out: a correlation does not prove that one thing causes another. Ice cream sales and sunburn both rise in summer, but one does not cause the other.
Exam tip
Grown-up tip. Ask the pupil to draw a line of best fit by eye, with about as many points above as below it.
Exercise 13E Scatter graphs and correlation
Non-calculatorMethod. Up from left to right.
- Read the data. Write down the values before working out the statistic.positive
- Decide. Both variables increase together.positive
- Write the answer. Give the answer with its unit.positive
Check. Points go up. ✓
Watch out. Positive means both go up.
Method. One goes up, the other goes down.
- Read the data. Write down the values before working out the statistic.negative
- Decide. The points go down from left to right.negative
- Write the answer. Give the answer with its unit.negative
Check. Negative correlation. ✓
Watch out. Down from left to right is negative.
Method. No pattern.
- Read the data. Write down the values before working out the statistic.no correlation
- Decide. The points are scattered with no pattern.no correlation
- Write the answer. Give the answer with its unit.no correlation
Check. No clear trend. ✓
Watch out. No pattern means no correlation.
Method. Read the y-value for x = 4.
- Read the data. Write down the values before working out the statistic.9
- Read. The y-value of the point is 9.9
- Write the answer. Give the answer with its unit.9 marks
Check. The point is (4, 9). ✓
Watch out. Read y for the given x.
Method. Change in y ÷ change in x.
- Read the data. Write down the values before working out the statistic.5
- Divide. (70 − 40) ÷ (8 − 2) = 30 ÷ 6.5
- Write the answer. Give the answer with its unit.5
Check. 5 × 6 = 30. ✓
Watch out. Use two points on the line.
Method. Use the line from (2, 40) with gradient 5.
- Go across 4. From x = 2 to x = 6 is 4 across.4
- Add the change. 40 + 5 × 4.60
- Write the answer. Give the answer with its unit.60
Check. The line gives y = 60 at x = 6. ✓
Watch out. Multiply the gradient by the change in x.
Method. An outlier is far from the others.
- Read the data. Write down the values before working out the statistic.(4, 20)
- Look. The first three points lie on a line; (4, 20) does not.(4, 20)
- Write the answer. Give the answer with its unit.(4, 20)
Check. (4, 20) is far from the trend. ✓
Watch out. Look for the point that does not fit the pattern.
Method. Taller with age.
- Read the data. Write down the values before working out the statistic.positive
- Decide. As age goes up, height goes up.positive
- Write the answer. Give the answer with its unit.positive
Check. Positive correlation. ✓
Watch out. Up from left to right.
Method. Down from left to right.
- Read the data. Write down the values before working out the statistic.negative
- Decide. One goes up as the other goes down.negative
- Write the answer. Give the answer with its unit.negative correlation
Check. Negative. ✓
Watch out. Down is negative.
Method. No pattern.
- Read the data. Write down the values before working out the statistic.none
- Decide. No trend.none
- Write the answer. Give the answer with its unit.no correlation
Check. No pattern. ✓
Watch out. No pattern means none.
Method. Close to the line means strong.
- Read the data. Write down the values before working out the statistic.strong
- Decide. The points are close to a line.strong
- Write the answer. Give the answer with its unit.strong positive correlation
Check. Strong and positive. ✓
Watch out. Close to the line is strong.
Method. Think about correlation and causation.
- Look. Correlation shows the two move together.move together
- Conclude. Something else could cause both: perhaps motivation.other causes
- Write the answer. Give the answer with its unit.Correlation does not prove cause
Check. A link does not prove a cause. ✓
Watch out. Correlation is not causation.
Comparing two sets of data
When two sets have the same average, the set with the smaller range is more consistent: its values are closer together. When averages are different, compare them directly, and then compare the spread.
Key ideas
- Compare an average (mean or median), and the spread (range).
- A smaller range means the values are more consistent.
- An outlier can change the mean a lot, but the median very little.
- Give a reason with the comparison: "the range is smaller, so Team A is more consistent".
Method. Compare the ranges, since the means are both 12.
- Find the ranges. Team A: 14 − 10 = 4. Team B: 15 − 9 = 6.4 and 6
- Compare. The smaller range is more consistent.Team A (4 < 6)
- Write the answer. Give the answer with its unit.Team A
Check. Both teams have mean 12, and 4 < 6. ✓
Watch out. Use the range to compare spread.
Method. Compare the ranges.
- Compare. The means are the same, so compare the spread.range 40 and 10
- Choose. The bigger range is class X.class X
- Write the answer. Give the answer with its unit.Class X
Check. Class X has the bigger range. ✓
Watch out. A bigger range means more spread.
Method. Sort the values, then find the middle.
- Sort. 3, 4, 6, 8, 9.3, 4, 6, 8, 9
- Middle. The middle value is 6.6
- Write the answer. Give the answer with its unit.6
Check. Two values each side of 6. ✓
Watch out. Sort before finding the median.
Watch out
Watch out: two sets with the same mean are not always the same. Compare the spread (range) too, since it may be very different.
Exam tip
Grown-up tip. Ask the pupil to say "the mean is the same, but the range is different" before choosing which set is more consistent.
Exercise 13F Comparing data sets
Non-calculatorMethod. Total and divide.
- Total. 2 + 4 + 6 + 8 + 10 = 30.30
- Divide. 30 ÷ 5.6
- Write the answer. Give the answer with its unit.6
Check. 6 × 5 = 30. ✓
Watch out. Divide by 5.
Method. Biggest minus smallest.
- Read the data. Write down the values before working out the statistic.8
- Subtract. 10 − 2.8
- Write the answer. Give the answer with its unit.8
Check. 2 + 8 = 10. ✓
Watch out. Use the extremes.
Method. Compare the ranges.
- Ranges. A: 4, B: 6.4 and 6
- Compare. The smaller range is more consistent.A
- Write the answer. Give the answer with its unit.Team A
Check. Both have mean 12. ✓
Watch out. The smaller range.
Method. Sort first (already sorted), then the middle value.
- Read the data. Write down the values before working out the statistic.6
- Middle. The middle of five values is the third.6
- Write the answer. Give the answer with its unit.6
Check. Two values each side of 6. ✓
Watch out. The middle of five is the third value.
Method. Compare the ranges.
- Read the data. Write down the values before working out the statistic.class X
- Compare. 40 is bigger than 10.class X
- Write the answer. Give the answer with its unit.Class X
Check. Class X has the bigger range. ✓
Watch out. Bigger range, more spread.
Method. Total and divide.
- Total. 60 + 70 + 80 + 70 + 70 = 350.350
- Divide. 350 ÷ 5.70
- Write the answer. Give the answer with its unit.70
Check. 70 × 5 = 350. ✓
Watch out. Divide by 5.
Method. Find both ranges.
- Ranges. P: 7 − 3 = 4. Q: 6 − 4 = 2.4 and 2
- Compare. Q has the smaller range.Q
- Write the answer. Give the answer with its unit.Set Q
Check. Both have mean 5. ✓
Watch out. Smaller range, more consistent.
Method. Think about what the average is used for.
- Look at the data. Shoe sizes are whole steps, so a mean may not be a real size.discrete steps
- Choose. The mode is the most common size, which is most useful for stock.mode
- Write the answer. Give the answer with its unit.The mode
Check. The most common size is the one to stock. ✓
Watch out. Choose the average that fits the data.
Method. The mean is pulled up more than the median by a large value.
- Read the data. Write down the values before working out the statistic.P
- Compare. P has a mean bigger than its median, so a large value pulls the mean up.P
- Write the answer. Give the answer with its unit.Set P
Check. The median stays at 4 but the mean is 5. ✓
Watch out. Look at the difference between mean and median.
Method. Biggest minus smallest.
- Read the data. Write down the values before working out the statistic.13
- Subtract. 22 − 9.13
- Write the answer. Give the answer with its unit.13
Check. 9 + 13 = 22. ✓
Watch out. Use the extremes.
Method. Sort first.
- Sort. 9, 14, 22.9, 14, 22
- Middle. The middle value is 14.14
- Write the answer. Give the answer with its unit.14
Check. One value each side. ✓
Watch out. Sort first.
Method. Total and divide.
- Total. 14 + 9 + 22 = 45.45
- Divide. 45 ÷ 3.15
- Write the answer. Give the answer with its unit.15
Check. 15 × 3 = 45. ✓
Watch out. Divide by 3.
Method. The total is 4 × 150 = 600.
- Total. 4 × 150 = 600.600
- Fourth. The three known heights add to 455, so 600 − 455.145
- Write the answer. Give the answer with its unit.145 cm
Check. 148 + 152 + 155 + 145 = 600. ✓
Watch out. Use the total.
Method. Think about what the mean tells you.
- Look at the mean. The mean is one number that does not show how spread out the values are.one number
- Compare the spread. Two sets can have the same mean but different ranges.different ranges
- Write the answer. Give the answer with its unit.The mean does not show the spread
Check. Compare the range too. ✓
Watch out. Look at the spread as well as the average.
Chapter summary
| Skill | Method |
|---|---|
| Data types | Categorical; numerical discrete (counted); numerical continuous (measured) |
| Charts | Bar charts start at 0; pictograms use a key; line graphs show change over time |
| Averages | Mean = total ÷ count; median = middle when sorted; mode = most common |
| Range | Biggest minus smallest: a measure of spread |
| Grouped data | Estimated mean = sum of (midpoint × frequency) ÷ total frequency |
| Scatter graphs | Positive, negative or no correlation; a line of best fit estimates values |
| Comparing data | Compare an average and the range; a smaller range is more consistent |
Can you…?
- I can tell categorical, discrete and continuous data apart
- I can read and draw frequency tables, bar charts, pictograms and line graphs
- I can find the mean, median, mode and range of a list and of a frequency table
- I can estimate the mean of grouped data using midpoints
- I can describe correlation and use a line of best fit to estimate a value
- I can compare two sets of data using an average and the range
Key terms
- categorical data
- data in groups described by words, such as colours
- discrete data
- numerical data that is counted in whole steps
- continuous data
- numerical data that is measured and can take any value in a range
- mean
- the total of the values divided by the number of values
- median
- the middle value when the values are in order
- mode
- the value that occurs most often
- range
- the biggest value minus the smallest value
- correlation
- a link between two variables, shown by the pattern of points on a scatter graph
- outlier
- a value that is far away from the others
Exercise 13Z Check-up
Non-calculatorMethod. Total and divide.
- Total. 5 + 7 + 9 = 21.21
- Divide. 21 ÷ 3.7
- Write the answer. Give the answer with its unit.7
Check. 7 × 3 = 21. ✓
Watch out. Divide by 3.
Method. Sort, then find the middle two.
- Sort. 4, 6, 8, 12.4, 6, 8, 12
- Middle. (6 + 8) ÷ 2.7
- Write the answer. Give the answer with its unit.7
Check. Between 6 and 8. ✓
Watch out. Halve the middle two.
Method. The most common value.
- Read the data. Write down the values before working out the statistic.3
- Count. 3 appears three times.3
- Write the answer. Give the answer with its unit.3
Check. Three is the most common. ✓
Watch out. Count each value.
Method. Biggest minus smallest.
- Read the data. Write down the values before working out the statistic.11
- Subtract. 15 − 4.11
- Write the answer. Give the answer with its unit.11
Check. 4 + 11 = 15. ✓
Watch out. Use the extremes.
Method. Multiply by the key.
- Read the data. Write down the values before working out the statistic.45
- Multiply. 4.5 × 10.45
- Write the answer. Give the answer with its unit.45 people
Check. 45 ÷ 10 = 4.5. ✓
Watch out. Half a symbol is half the key.
Method. Midpoints times frequencies, divided by 5.
- Multiply and add. 2 × 5 + 3 × 15 = 10 + 45 = 55.55
- Divide. 55 ÷ 5.11
- Write the answer. Give the answer with its unit.11
Check. 11 × 5 = 55. ✓
Watch out. Use the midpoints.
Method. Down from left to right.
- Read the data. Write down the values before working out the statistic.negative
- Decide. One goes up as the other goes down.negative
- Write the answer. Give the answer with its unit.negative
Check. Negative correlation. ✓
Watch out. Down means negative.
Method. Add the frequencies.
- Read the data. Write down the values before working out the statistic.10
- Add. 3 + 5 + 2.10
- Write the answer. Give the answer with its unit.10
Check. 10 − 5 = 5 = 3 + 2. ✓
Watch out. Add them all.
Method. Find the group with 23 between its ends.
- Read the data. Write down the values before working out the statistic.20 to 25
- Compare. 20 ≤ 23 < 25.20 to 25
- Write the answer. Give the answer with its unit.20 to 25
Check. 23 is between 20 and 25. ✓
Watch out. Check the ends of each group.
Method. The total is 24.
- Total. 4 × 6 = 24.24
- Fourth. 24 − (4 + 6 + 8) = 24 − 18.6
- Write the answer. Give the answer with its unit.6
Check. 4 + 6 + 8 + 6 = 24. ✓
Watch out. Use the total.
Total 21 marks. Allow about 21 minutes.
Exercise 13X Practice test questions
Non-calculatorMethod. Goals are counted.
- Read the data. Write down the values before working out the statistic.discrete
- Decide. Goals are whole numbers, counted.discrete
- Write the answer. Give the answer with its unit.numerical, discrete
Check. Whole goals only. ✓
Watch out. Counts are discrete.
Method. Sort, then take the middle.
- Sort. 3, 5, 8.3, 5, 8
- Middle. The middle value is 5.5
- Write the answer. Give the answer with its unit.5
Check. Two values around 5. ✓
Watch out. Sort first.
Method. Total and divide.
- Total. 3 + 5 + 7 + 9 = 24.24
- Divide. 24 ÷ 4.6
- Write the answer. Give the answer with its unit.6
Check. 6 × 4 = 24. ✓
Watch out. Divide by 4.
Method. Multiply the symbols by the key.
- Read the data. Write down the values before working out the statistic.24
- Multiply. 3 × 8.24
- Write the answer. Give the answer with its unit.24 books
Check. 24 ÷ 8 = 3. ✓
Watch out. Use the key.
Method. Multiply each value by its frequency, add, and divide by the total frequency.
- Multiply. 2 × 3 + 3 × 5 + 4 × 2 = 6 + 15 + 8 = 29.29
- Divide. The total frequency is 3 + 5 + 2 = 10.29 ÷ 10 = 2.9
- Write the answer. Give the answer with its unit.2.9
Check. 2.9 × 10 = 29. ✓
Watch out. Use the frequencies as multipliers.
Method. Range: biggest minus smallest. Mode: most common.
- Range. 12 − 4 = 8.8
- Mode. 7 occurs twice, more than any other value.7
- Write the answer. Give the answer with its unit.range 8, mode 7
Check. Range 8 and mode 7. ✓
Watch out. Check both.
Method. The total is 5 × 10 = 50.
- Total. 5 × 10 = 50.50
- Fifth. 50 − (8 + 9 + 12 + 11) = 50 − 40.10
- Write the answer. Give the answer with its unit.10
Check. 8 + 9 + 12 + 11 + 10 = 50. ✓
Watch out. Use the total.
Method. Midpoints times frequencies, divided by 10.
- Multiply and add. 4 × 155 + 6 × 165 = 620 + 990 = 1610.1610
- Divide. 1610 ÷ 10.161
- Write the answer. Give the answer with its unit.161 cm
Check. 161 × 10 = 1610. ✓
Watch out. Use the midpoints.
Method. Find the gradient, then use the line.
- Gradient. (30 − 10) ÷ 10 = 2.2
- Estimate. y = 10 + 2 × 7.24
- Write the answer. Give the answer with its unit.24
Check. The line through (7, 24). ✓
Watch out. Use the gradient from the two points.
Method. Think about outliers.
- Look. A few very expensive houses are outliers.outliers
- Compare. The mean is pulled up, but the median stays near the typical price.typical
- Write the answer. Give the answer with its unit.The median is not affected by a few very high prices
Check. The median shows the typical price. ✓
Watch out. Outliers affect the mean much more.