Data and Its Collection (O Level 4040): Practice Questions

These are original questions written for Marlbridge, for revision and practice on this content. They are not reproduced past-paper questions, and they do not replicate the exam’s exact structure, question count or mark tariffs — examination boards hold copyright in their own papers. Use these alongside the official past papers available free from your board.

Related: Data and Its Collection revision notes

---

Section A

1. State whether each of the following is qualitative, discrete quantitative or continuous quantitative data: (a) the number of goals scored in a football match (b) the time taken to run 100 m (c) the make of car owned by a family [3]

2. State two differences between primary and secondary data. [2]

Section B

3. A school with 1,200 students wants to find out how students travel to school. The head teacher considers two methods: (i) surveying every student, (ii) surveying a sample of 100 students selected using stratified sampling by year group.

(a) State the name given to method (i). [1] (b) Give one advantage and one disadvantage of method (i) compared with method (ii). [2] (c) Explain how the head teacher should select the stratified sample, given the school has 6 year groups of unequal size. [3] (d) Suggest one source of bias that could still affect the survey’s results even with a well-chosen sample. [2]

4. A researcher wants to survey the reading habits of adults in a town. She stands outside a bookshop on a Saturday morning and asks every 5th person who passes.

(a) Name the sampling method used. [1] (b) Explain two reasons why this sample may not be representative of all adults in the town. [4] (c) Suggest one improvement to the sampling method. [2]

Section C

5. A factory has 240 workers in production, 90 in sales and 30 in admin. A stratified sample of 36 workers is required.

(a) Calculate how many workers should be sampled from each department. [3]

(b) Explain how workers within each stratum should then be chosen. [1]

6. A researcher is designing a questionnaire.

(a) State two features of well-designed response options. [2]

(b) Explain why a pilot survey is used before the full questionnaire is deployed. [2]

(c) A student claims that increasing the sample size removes bias from a survey. Explain why this claim is incorrect. [2]

---

Answers

1. (a) Discrete quantitative [1]. (b) Continuous quantitative [1]. (c) Qualitative [1].

2. Any two, e.g.: primary data is collected first-hand by the researcher for their specific purpose, while secondary data was collected by someone else, often for a different purpose [1]; primary data is usually more accurate/relevant to the exact question but more time-consuming and costly to collect, while secondary data is quicker and cheaper to obtain but may not fit the researcher’s exact needs [1].

3. (a) Census [1]. (b) Advantage: no sampling error, since every student is included, giving fully accurate results [1]. Disadvantage: far more time-consuming and costly than sampling 100 students [1]. (c) The 1,200 students should be divided into their 6 year-group strata [1]; the sample of 100 should be split between year groups in proportion to each year group’s size in the school [1]; within each stratum, students should then be chosen using simple random sampling [1]. (d) Any one with explanation, e.g. non-response bias — students who dislike the survey topic or rarely attend school may be less likely to respond, skewing results toward more typical travel patterns [2]; or the day/time of the survey could bias results if travel method varies by day (e.g. sports-day transport arrangements) [2].

4. (a) Systematic in form (every 5th person), but with no sampling frame and no defined random start, this is opportunity sampling in substance [1]. (b) Any two with explanation: the sample only includes people near a bookshop, who are likely to already be more interested in reading than the general adult population, so the results will overstate reading habits [2]; the survey is only conducted on a Saturday morning, which excludes adults who work or are unavailable at that time, so the sample may not represent all adults’ schedules and habits [2]. (c) Any reasonable improvement, e.g. survey people across several different locations (not just outside a bookshop) and at different times/days, to reduce the bias toward people who are already likely to be readers [2].

5. (a) Total = 240 + 90 + 30 = 360; sampling fraction = 36 ÷ 360 = 1/10 [1]. Production: 240 ÷ 10 = 24; Sales: 90 ÷ 10 = 9; Admin: 30 ÷ 10 = 3 [2].

(b) Within each stratum, workers should be chosen using simple random sampling [1] — a stratified sample is still random, just random within groups.

6. (a) Any two: response options should be exhaustive, covering every possible answer [1]; and non-overlapping (mutually exclusive), so no respondent fits more than one category [1].

(b) A pilot survey tests the instrument before full deployment [1], identifying unclear wording, ambiguous questions or design problems so they can be fixed before the real data collection, saving time and improving data quality [1].

(c) Increasing sample size reduces sampling error, making the sample statistic a more precise estimate [1], but it does not remove bias — a biased sampling method (such as an incomplete sampling frame or non-response) produces a systematically skewed result regardless of how large the sample is [1].

---

Where marks are usually lost

• Confusing “discrete” with “small whole number” — the test is whether the variable can only take separate, specified values (discrete) or any value in a range (continuous), not its size. “Counted vs measured” is a usual rule of thumb, not the deciding test.
• Describing a census as always being “more accurate” without acknowledging its cost and practicality trade-offs.
• Explaining stratified sampling as equal group sizes rather than proportional group sizes.
• Naming a source of bias without explaining why it skews the results in a particular direction.