Revision Library
Choose a subject
Menu
GCSE Statistics · Topic guide

Collecting Data

Collecting data covers the practical methods used to gather information for a statistical investigation, including surveys and questionnaires, observation, experiments, and using data that already exists (secondary data). The method chosen depends on the type of data needed, the population being studied, and practical factors like time and cost. GCSE Statistics exams often ask you to identify a suitable method or to critique a data collection method used in a given scenario.

Foundation & HigherCollecting DataEdexcelAQACCEA

Before you start

Make sure you're comfortable with these topics first:

Method

  1. Decide what data you need (its type, and whether primary or secondary data is appropriate) before choosing a method.
  2. For primary data, choose between a questionnaire/survey (asking people directly), an experiment (controlling variables to test something), or observation (recording what happens without intervening).
  3. For secondary data, identify a reliable existing source, such as government statistics or published research, and check it is relevant and up to date.
  4. Consider practical factors: cost, time available, and how easy the data is to access, since these can limit which method is realistic.
  5. Check the method for possible sources of bias, such as leading questions, a non-random sample, or observer effects.
  6. Pilot the method on a small group first if possible, to catch problems before collecting the full data set.

Common mistakes

  • MistakeConfusing primary and secondary data, for example calling data 'secondary' just because it was collected using a formal method like a survey, rather than basing the distinction on who collected it and why.

    InsteadThe distinction is about who collected it and why, not the method used: a survey the researcher carries out herself is primary data, while pulling someone else's past survey results off a website is secondary data, whatever method that other survey used.

  • MistakeDescribing a flaw in a method (for example 'the sample is biased') without explaining why it is biased, when the command word is 'explain' or 'evaluate' rather than just 'state'.

    InsteadGive the mechanism, not just the label: instead of 'the sample is biased', write 'the sample is biased because only people motivated enough to fill in a comment card respond, so the results over-represent strong opinions compared with typical members'.

  • MistakeRecommending an experiment for a question that is really about describing or comparing something as it naturally occurs, rather than testing a cause-and-effect relationship by controlling variables.

    InsteadUse an experiment only when something is being deliberately controlled and tested, such as whether a fertiliser causes plants to grow taller; for finding out how long people currently spend commuting, a survey or observation is appropriate instead.

Worked examples

Example 1

A student is investigating whether it rains more in the north of the UK than the south. Suggest a suitable method of collecting the data she needs, and explain your choice.

  1. Identify the data needed: rainfall amounts (in mm) for locations in the north and south of the UK over the same time period.
  2. Consider primary data collection: setting up rain gauges herself in several towns would take a long time and be hard to do accurately across a whole country.
  3. Consider secondary data: the Met Office already publishes reliable rainfall records for towns across the UK.
  4. Choose secondary data, since it is already collected accurately over a long period and covers far more locations than she could measure herself.
  5. Final answer: use secondary data (existing published rainfall records), because it is more reliable, wide-reaching and practical than collecting primary data herself.

Example 2

A local council wants to know whether residents on a street support a proposed new speed bump. A councillor telephones every resident whose landline number is listed in the phone book, one evening the week before the vote takes place. (a) Name one group of residents this method is likely to miss completely, and explain why. (b) The councillor's report claims the results show the views of 'the whole street'. Comment on whether this claim is justified. (c) Suggest one change to the method that would make the sample more representative.

  1. Many residents, especially younger ones, do not have a landline number listed in a phone book, so this method is likely to miss them completely.
  2. Because of this, the councillor's claim to represent the views of 'the whole street' is not justified: the sample only reaches residents with a listed landline, not everyone living there.
  3. A more representative method would be to deliver a short written survey, or a link to an online survey, to every household on the street directly, rather than relying on phone book listings.
  4. This reaches households with no landline too, so the sample is more likely to reflect the views of everyone on the street, not just one group.
  5. Final answer: the phone-book method misses residents with no listed landline (especially younger residents), so the 'whole street' claim is not justified; delivering a survey to every household directly would give a more representative sample.

Example 3

A fictional community arts centre has 300 registered adult members. Its email contact list contains 260 members; 40 members are missing from this sampling frame. The centre randomly selects 52 names from the email list and sends each person a survey. Thirty-nine selected members reply. Work out how many people were omitted from the frame, how many selected people did not respond, and the response rate among those selected. Explain why the two groups are different and whether the replies automatically represent all 300 members.

  1. The target population is all 300 registered members, but the sampling frame has only 260 names. So 300 - 260 = 40 members are omitted before any names are selected.
  2. The centre selects 52 people from the 260 names. Of those selected, 39 reply, so 52 - 39 = 13 selected people do not respond.
  3. The 40 omitted members were never on the list and could not be selected. The 13 non-respondents were selected from the list but did not reply. These are different points where people can be missing.
  4. The response rate among those selected is 39 / 52 x 100 = 75%. This describes replies from the selected group; it does not include the 40 people omitted from the frame.
  5. The replies do not automatically represent all 300 members: 40 had no chance of selection, and the 13 selected non-respondents may have different views from those who replied.
  6. Final answer: 40 members were omitted from the sampling frame, 13 selected members did not respond, and 75% of those selected replied. The two groups are different because only the second group was selected; the replies alone cannot establish that all 300 members are represented.

Practice questions

Q1[1 mark]State whether interviewing shoppers face-to-face about their favourite supermarket is primary or secondary data collection.Show answer

Answer: Primary (the researcher collects it first-hand)

Got it right?
Q2[1 mark]A student uses figures from a government website for her project. Is this primary or secondary data?Show answer

Answer: Secondary (it already existed before her investigation)

Got it right?
Q3[1 mark]Give one advantage of using a questionnaire to collect data.Show answer

Answer: It can reach a large number of people relatively cheaply and quickly (accept any valid advantage)

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q4[1 mark]Give one disadvantage of an observation study.Show answer

Answer: People may behave differently when they know they are being watched (observer effect), or it can be time-consuming (accept any valid disadvantage)

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q5[1 mark]A question asks: 'Don't you agree that the new bus timetable is an improvement?' State what is wrong with this question.Show answer

Answer: It is a leading question, which encourages a particular (biased) answer

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q6[1 mark]State one advantage secondary data has over primary data for a project on rainfall over the last 50 years.Show answer

Answer: It already exists over that time period, so the researcher does not need to have been collecting it for 50 years themselves

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 GCSE Statistics exam paper, with a full mark scheme.

Exam tips

  • State whether data is primary or secondary by asking who collected it and for what purpose, not by the method used - a survey can be either, depending on who ran it and when.
  • An 'explain' or 'evaluate' question about a data collection method needs the reason a flaw matters, not just the flaw named (such as 'biased' or 'not random') on its own.
  • Match the method to the question: choose an experiment only when a cause is being deliberately tested by controlling variables; choose a survey, observation or secondary data to simply describe or measure something.
Q1[2 marks]A researcher wants to find out how long people spend commuting to work. State one primary method she could use to collect this data, and one advantage of that method.Show mark scheme

Tick each line you got.

Nothing ticked yet - 2 available

Got it right?
Q2[3 marks]A gym wants to know how satisfied its members are. It leaves a box of comment cards at the reception desk. (a) State one problem with this method of data collection. (b) Suggest a better method. (c) Give one reason your suggested method is better.Show mark scheme

Tick each line you got.

Nothing ticked yet - 3 available

Got it right?
Q3[3 marks]A scientist wants to test whether a new fertiliser increases the height of tomato plants. (a) State the type of data collection method most suitable (survey, observation, or experiment). (b) Explain your choice. (c) State one variable she should keep the same between the group given fertiliser and the group not given fertiliser.Show mark scheme

Tick each line you got.

Nothing ticked yet - 3 available

Got it right?

See real GCSE Statistics 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 Collecting Data worksheet pack - 28 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 8 of GCSE Statistics Foundation Essentials 1 and chapter 8 of GCSE Statistics Higher Essentials 1, the whole course as one free printable PDF. Its worksheet is also chapter 8 of GCSE Statistics Foundation Topic Workbook 1 and chapter 1 of GCSE Statistics Higher Topic Workbook 2, free printable practice books.

Other versions of this worksheet:

Keep going

Not quite what you needed?

Tell us what is missing on Collecting Data, or which topic to write up next.

Build a full practice pack.