GCSE Statistics Higher Short Paper A
Covers Collecting Data, Sampling Methods, Tables and Frequency Distributions and 3 more.
Questions
Question 1 [2 marks]
Tables and Frequency Distributions
A class of 28 students is grouped by favourite subject in the two-way table. A ? marks a missing value.
| Subject | Year 10 | Year 11 | Total |
|---|---|---|---|
| Maths | 6 | ? | 13 |
| English | 8 | 7 | 15 |
| Total | 14 | 14 | 28 |
Find the missing value for the number of Year 11 students whose favourite subject is Maths.
Question 2 [3 marks]
Collecting Data
A researcher records the time taken (in seconds, to 2 decimal places) for sprinters to finish a race, and also records the lane number each sprinter ran in.
Classify the underlying running time (before rounding) and the lane number as continuous quantitative, discrete quantitative or qualitative categorical data. Give a reason for one of your classifications.
Question 3 [3 marks]
Histograms and Frequency Density
Explain why, when class widths are unequal, it would be misleading to draw a histogram using frequency (rather than frequency density) as the bar height.
Question 4 [3 marks]
Sampling Methods
A researcher wants to survey opinions of shoppers in a large shopping centre.
Before approaching anyone, she sets a fixed target number of interviews for each age and gender group to match the population proportions, with 50 interviews in total. At one entrance she approaches available shoppers and interviews only willing people whose group target has not yet been met. She stops when every group has reached its target.
Name the overall sampling method and explain one weakness of it, including how that weakness could bias the results.
Question 5 [3 marks]
Collecting Data
A company collects data on the number of items sold in its own shop each day (primary data), and also downloads national retail sales figures published by the government (secondary data).
Explain the difference between primary and secondary data, and give one advantage of using secondary data in this context.
Question 6 [4 marks]
Averages and Range
Six numbers have a mean of 8. A seventh number is added and the new mean of all seven numbers is 9.
Find the value of the seventh number.
Question 7 [4 marks]
Statistical Diagrams
A pictogram shows the number of bikes sold by a shop over January to March, where each bicycle symbol represents 5 bikes: January 4 symbols, February 6 symbols, March 3 symbols.
The shop sold a total of 90 bikes over January to April.
Calculate the number of bikes sold in January, February and March combined, and hence find how many bikes, and how many full symbols, should be drawn for April.
Question 8 [6 marks]
Sampling Methods
A researcher uses cluster sampling across a county's schools of unequal size to estimate average pocket money among Year 8 pupils. She randomly selects 4 schools with Year 8 pupil numbers 60, 85, 40 and 95, and surveys every Year 8 pupil in each.
Calculate the total sample size, calculate this as a percentage of the county's 2500 Year 8 pupils (1 decimal place), and explain why estimating the county-wide mean pocket money by simply averaging the four schools' individual means, unweighted, could be misleading given the schools have different sizes.
Question 9 [6 marks]
Averages and Range
The mean of 15 numbers was calculated as 20. It was later discovered that one value had been misread as 38 when it should have been 83.
Find the correct mean of the 15 numbers, and state by how much the mean changed as a result of the correction.
Question 10 [6 marks]
Statistical Diagrams
A newspaper wants to compare how 150 Year 10 students and 90 Year 11 students each spend their free time, using either two separate pie charts (one per year group) or one composite bar chart.
Explain one advantage of using two pie charts here, explain one problem that can arise when comparing two pie charts of different total sample sizes unless this is made clear to the reader, and describe how this problem could be addressed. Develop the advantage and the problem, and describe two different ways to address the problem.
Model solutions
| Question 1[2 marks] | |
|---|---|
| Answer or working | Marks |
| using the Maths row total minus the Year 10 value, or the Year 11 column total minus the English value: 13 - 6 (or 14 - 7) | M1 |
| 7 students | A1 |
| Question 2[3 marks] | |
|---|---|
| Answer or working | Marks |
| running time is continuous quantitative data | B1 |
| lane number is qualitative categorical data (accept nominal data) | B1 |
| a valid reason for either classification: time can take any value in a range before rounding, or a lane number identifies a lane rather than measuring or counting a quantity | B1 |
| Final answer: Running time is continuous quantitative data. Lane number is qualitative categorical (nominal) data. A valid reason is that underlying time can take any value in a range before rounding, or that a lane number labels a lane rather than measuring a quantity. | |
| Question 3[3 marks] | |
|---|---|
| Answer or working | Marks |
| stating that a histogram bar area, rather than its height alone, represents class frequency | B1 |
| explaining that using frequency as height gives area = frequency x width, so unequal widths distort area comparisons | B1 |
| explaining that height = frequency/width makes area = frequency and allows comparison of concentration per unit interval | B1 |
| Final answer: Histogram area represents frequency. Using frequency as height makes area equal frequency x class width, exaggerating wider classes. Frequency density = frequency/width restores area = frequency. | |
| Question 4[3 marks] | |
|---|---|
| Answer or working | Marks |
| quota sampling | B1 |
| identifying one weakness, e.g. shoppers who use other entrances cannot be selected, or only willing shoppers take part | B1 |
| developing the identified weakness: the excluded shoppers or unwilling shoppers may have different views, so matching the quotas does not remove this selection bias | B1 |
| Final answer: Quota sampling: fixed group targets are set before selection and filled without random selection. Shoppers who use other entrances cannot be selected. If their views differ from those entering here, results may be biased even though the age and gender quotas are met. | |
| Question 5[3 marks] | |
|---|---|
| Answer or working | Marks |
| a correct definition of primary data (collected first-hand, by or for the researcher for this purpose) | B1 |
| a correct definition of secondary data (already collected by someone else, often for another purpose) | B1 |
| a valid advantage of secondary data, e.g. it saves time and cost since it already exists | B1 |
| Final answer: Primary data is collected directly by the researcher for their own purpose; secondary data already exists, collected by someone else. Advantage: it saves time and cost because it does not need to be collected again. | |
| Question 6[4 marks] | |
|---|---|
| Answer or working | Marks |
| the sum of the original six numbers: 6 x 8 = 48 | M1 |
| the sum of all seven numbers: 7 x 9 = 63 | M1 |
| subtracting: 63 - 48 | M1 |
| the seventh number = 15 | A1 |
| Final answer: 15 | |
| Question 7[4 marks] | |
|---|---|
| Answer or working | Marks |
| January to March bikes: 4x5 + 6x5 + 3x5 | M1 |
| 65 bikes | A1 |
| April's bikes: 90 - 65 | M1 |
| 25 bikes, drawn as 5 full symbols (25/5) | A1 |
| Final answer: January to March = 65 bikes combined. April = 25 bikes = 5 full symbols. | |
| Question 8[6 marks] | |
|---|---|
| Answer or working | Marks |
| the total sample: 60 + 85 + 40 + 95 | M1 |
| 280 pupils | A1 |
| the percentage: 280/2500 x 100 | M1 |
| 11.2% | A1 |
| a valid explanation, e.g. an unweighted average of the four school means gives equal weight to a school of 40 pupils and a school of 95 pupils, even though the larger school contributes more individual pupils to the true county-wide mean | B1 |
| a further valid point, e.g. the correct approach is a weighted mean, weighting each school's mean by its number of pupils | B1 |
| Final answer: Total sample = 280 pupils = 11.2% of the county's Year 8 pupils (1 dp). A simple unweighted average of the four school means treats a 40-pupil school the same as a 95-pupil school, so it would not reflect their true share of pupils; a weighted mean, weighted by school size, is needed instead. | |
| Question 9[6 marks] | |
|---|---|
| Answer or working | Marks |
| the original total: 15 x 20 | M1 |
| original total = 300 | A1 |
| the corrected total: 300 - 38 + 83 | M1 |
| corrected total = 345 | A1 |
| the corrected mean: 345/15 | M1 |
| corrected mean = 23, an increase of 3 from the original mean of 20 | A1 |
| Final answer: Corrected mean = 23, an increase of 3 from the original mean of 20. | |
| Question 10[6 marks] | |
|---|---|
| Answer or working | Marks |
| a valid advantage, e.g. each pie chart clearly shows the proportion of that year group's time spent on each activity, easy for a reader to see at a glance | B1 |
| a developed point, e.g. proportions matter for comparing patterns of time use, not raw numbers, so pie charts suit comparing shapes across groups | B1 |
| the problem that equal-sized circles can conceal the different sample sizes of 150 and 90 | B1 |
| a distinct consequence, e.g. equal sector angles in the two pies can represent different numbers of pupils, so proportions alone do not compare counts | B1 |
| a valid fix, e.g. scale the radius of each pie chart so its area is proportional to its sample size (a comparative pie chart) | B1 |
| a further valid fix, e.g. simply state each group's total sample size alongside its pie chart so the reader is not misled | B1 |
| Final answer: Pie charts clearly show each year group's own proportions, useful for comparing patterns of time use. However, two same-sized pie charts can look equally significant even though 150 and 90 are different sample sizes, misleading a reader about their relative importance. This can be addressed by scaling the pie chart radii so their areas are proportional to sample size, or by stating each total alongside the chart. | |