Cambridge IGCSE Statistics: Data and Its Collection (0479)

This guide covers Topic 1 Data and Its Collection, the first of twelve topics in Cambridge IGCSE Statistics (0479), for examination 2027. All candidates take two compulsory papers, each worth 50% of the qualification, and both draw on this foundational topic.

Where this fits in 0479

Topic 1 establishes how data is collected and classified before the syllabus moves through Representation of data, Frequency distributions, Measures of central tendency, and on through probability and index numbers. Every later topic assumes a secure understanding of sampling methods and data types established here.

Syllabus coverage

CAMBRIDGE IGCSE STATISTICS (0479) — TOPIC 1 DATA AND ITS COLLECTION

Topic 1 covers the terms population, sample, census and representative sample; the features of different sampling methods (simple random, systematic, stratified and quota sampling); how sampling methods can be biased; using random number tables to select samples; the use of open and closed questions in surveys; and classifying data as qualitative, quantitative, discrete or continuous.

How to approach it

Because sampling method questions often ask candidates to select an appropriate method for a described scenario and justify the choice, practise applying each method to different scenarios rather than only memorising definitions – knowing when stratified sampling is more appropriate than simple random sampling, for instance, is tested more often than defining the terms alone. Using random number tables is a practical skill that needs repetition, so work through several sample- selection exercises until the process (defining the population, numbering it, then reading the table) becomes automatic. Classifying data correctly (qualitative versus quantitative, discrete versus continuous) is a small but easily-lost-marks area, so practise classifying a wide range of real-world data examples quickly and accurately.

Official syllabus

Cambridge IGCSE Statistics (0479) syllabus for examination in 2027 — cambridgeinternational.org.

Types of data

Qualitative data describes a quality and cannot be measured numerically — eye colour, brand of car. Quantitative data is numerical, and divides further:

• Discrete — takes only specific values, usually from counting. Number of children, shoe size.
• Continuous — takes any value within a range, from measuring. Height, mass, time.

Continuous data is always recorded to a degree of accuracy, so a height recorded as 168 cm lies in the interval 167.5 <= h < 168.5. Getting those class boundaries right is what makes later grouped calculations work.

Data is primary if collected by the investigator for the purpose at hand, and secondary if it already exists. Primary data is relevant and its reliability is known, but it is slow and costly; secondary is quick and cheap but may be outdated, biased or collected for a different purpose.

Populations and sampling

A census surveys every member of the population — completely accurate but expensive, slow, and impossible where testing destroys the item. A sample surveys part of it, and the method determines whether conclusions are valid.

Method	How it works	Weakness
Simple random	Every member equally likely, using random numbers	Needs a full sampling frame
Systematic	Every nth member from a random start	Bias if the list has a pattern
Stratified	Population split into groups, sampled in proportion	Strata must be known
Quota	Interviewer fills set numbers per category	Not random, interviewer bias
Opportunity	Whoever is available	Highly unrepresentative

Larger samples are more reliable but cost more. Bias arises from an incomplete sampling frame, non-response, leading questions, self-selection, or the interviewer effect, where respondents answer differently depending on who is asking. A larger sample reduces sampling error — the random variation between samples — but does not remove bias: a biased method stays biased at any size, however large, since bias is a systematic fault in the method itself rather than a matter of random variation. These two ideas are frequently confused but need to be argued separately.

Collecting data

A good questionnaire uses clear, unambiguous language, avoids leading questions, provides response options that do not overlap and cover every possibility, and keeps sensitive questions to the end. A pilot survey tests it on a small group first, exposing ambiguous wording before the full survey runs.

Worked example

A school of 900 students has 400 in Key Stage 3, 350 in Key Stage 4 and 150 in Key Stage 5. Take a stratified sample of 60.

Sampling fraction = 60 / 900 = 1/15

KS3: 400 / 15 = 26.7  -> 27
KS4: 350 / 15 = 23.3  -> 23
KS5: 150 / 15 = 10    -> 10
                        ---
                        60

Round carefully so the parts still total 60 — a frequent source of a lost mark.

Common mistakes

Classifying shoe size as continuous because sizes include halves — it is discrete, since only specific values occur. Writing overlapping classes such as 0–10 and 10–20. Describing a stratified sample as choosing equal numbers from each group rather than proportional numbers. Saying a larger sample removes bias — it reduces sampling error, but a biased method stays biased at any size. Forgetting to state the random element in systematic sampling.

Quick revision checklist

• Classify data as qualitative or quantitative, discrete or continuous, primary or secondary.
• State class boundaries for continuous data recorded to a given accuracy.
• Compare census and sample, and describe each sampling method with its weakness.
• Calculate a stratified sample, rounding so the totals agree.
• Identify sources of bias and write unbiased questionnaire questions.
• Explain the purpose of a pilot survey.