Edexcel A-level Mathematics · S · Statistics
S1 Statistical sampling
Describe the main sampling methods, compare their strengths and weaknesses, identify sources of bias and use sample data to estimate population values.
1/6A sample lets us learn about a whole population
- A sample lets us learn about a whole population
- Random sampling methods avoid personal choice in selection
- Stratified sampling reflects the groups within a population
- Non-random methods are quicker but less reliable
- Bias occurs when a sample favours some members
- Sample data give estimates of population values
- Check your recall
- Practice: 10 questions
Part 1 of 6: A sample lets us learn about a whole population
A school wants to know how its students travel to class. Asking all 1500 students takes time and effort. Asking a smaller group is quicker and cheaper.
The population is the whole set of people or items being studied. A census observes every member of it. A sample is a smaller group taken from the population.
A census is accurate, but often impractical. It is also impossible when testing destroys each item, as with testing how long fuses last before they fail.
Key terms · tap one for its definition
population
A population is the whole set of individuals or items about which information is wanted.
census
A census is a survey that collects data from every member of the population.
sample
A sample is a selected subset of the population from which data are collected.
Part 2 of 6: Random sampling methods avoid personal choice in selection
Now that you know what a sample is, consider how to choose one. A sampling frame is a list of every member of the population. Random methods select from this list.
In a simple random sample, every member has the same chance of selection. Number the members and generate random numbers. Ignore repeated numbers, so that no member is chosen twice.
In systematic sampling, you pick members at regular intervals from the list. For members from a population of , the interval is . Choose the first member at random within the first interval.
Worked example
Taking a systematic sample
- Interval: .
- Choose a random starting number from 1 to 15, for example 7.
- Select members 7, 22, 37 and so on, adding 15 each time, until 40 members are chosen.
Answer: The sample is every 15th member, starting from a randomly chosen member within the first 15.
Key terms · tap one for its definition
sampling frame
A sampling frame is a list of all members of the population from which a sample is chosen.
simple random sample
A simple random sample of size is one in which every possible sample of that size is equally likely.
systematic sampling
Systematic sampling selects members at regular intervals from an ordered list, starting from a randomly chosen position.

Quick check
One question on the part you just read
Easy
Show answer and explanation
Answer: B · Worked explanation
Part 3 of 6: Stratified sampling reflects the groups within a population
A simple random sample can miss a small group by chance. Stratified sampling prevents this. Split the population into groups, such as year groups, then sample from each.
In stratified sampling, the number taken from each group is in proportion to its size. Use . Round to the nearest whole number and check the total. Rounding can leave the total one too high or too low. Then take a simple random sample of that size from each group.
Worked example
Stratified sample sizes
- Year 12: .
- Year 13: .
- Foundation year: .
- Check: .
Answer: Take 16 students from Year 12, 14 from Year 13 and 10 from the foundation year, each by simple random sampling.
Key term
stratified sampling
Stratified sampling divides the population into groups and takes a simple random sample from each in proportion to its size.
Part 4 of 6: Non-random methods are quicker but less reliable
Random methods need a sampling frame, which is not always available. Non-random methods avoid this need. They are often used in street surveys.
In quota sampling, an interviewer fills fixed numbers from each group, such as 20 men and 20 women. The interviewer chooses who to ask. In opportunity sampling, you take whoever is available and willing.
These methods are cheap, quick and need no frame. But not every member has a known chance of selection. The results may not represent the population.
Strengths and weaknesses of sampling methods
- Method
- Simple random
- Advantage
- Free from selection bias
- Disadvantage
- Needs a full list; may miss small groups
- Method
- Systematic
- Advantage
- Quick; spreads evenly
- Disadvantage
- A pattern in the list may cause bias
- Method
- Stratified
- Advantage
- Represents every group
- Disadvantage
- Needs group sizes; more work
- Method
- Quota
- Advantage
- No frame needed; groups included
- Disadvantage
- Non-random; interviewer may choose
- Method
- Opportunity
- Advantage
- Easy and cheap
- Disadvantage
- Often unrepresentative; non-random
Key terms · tap one for its definition
quota sampling
Quota sampling selects a fixed number of individuals from each group, with the interviewer choosing who is asked.
opportunity sampling
Opportunity sampling selects the individuals who are available at the time and willing to take part.

Quick check
One question on the part you just read
Easy
Show answer and explanation
Answer: A · Worked explanation
Part 5 of 6: Bias occurs when a sample favours some members
A sample can be poor even when it is large. The cause is often bias: the method of selection makes some members more likely to be chosen than others. The sample then differs from the population in a consistent direction.
- an incomplete or out-of-date sampling frame
- selection by an interviewer’s personal choice
- volunteers who choose themselves to respond
- sampling at an unrepresentative time or place
Interviewing people outside a gym about exercise habits would overestimate how active a town is. Gym users are far more likely to be selected than other residents.
Key term
bias
Bias is a systematic error in selecting or measuring a sample that makes it unrepresentative of the population.
Part 6 of 6: Sample data give estimates of population values
Sampling is useful because sample data let us estimate unknown values. An estimate is a value calculated from a sample to approximate a population value. The sample mean estimates the population mean, and the sample proportion estimates the population proportion. A mean journey time of 12.4 minutes in the sample estimates 12.4 minutes for the population.
To estimate a population total, multiply the sample proportion by the population size. Estimates vary from sample to sample. They are most reliable from large, unbiased samples.
Worked example
Estimating a total
- Sample proportion: .
- Multiply by the population size: .
Answer: About 450 students walk to college.
Key term
estimate
An estimate is a value calculated from sample data to approximate an unknown population value.
Check your recall[13 marks]
6 written questions. Answer each one in your head or on paper, then open the mark scheme.
- 1.Define[1 mark]
Define a sampling frame.
Show mark schemeHide mark scheme
Model answer
A sampling frame is a list of all members of the population from which a sample is chosen.
- 1 mark for stating that it is a list of all members of the population
- 2.Describe[3 marks]
Describe how to take a systematic sample of 30 from a population of 600 listed in order.
Show mark schemeHide mark scheme
Model answer
The interval is . Choose a random starting member from the first 20, then select every 20th member after that.
- 1 mark for calculating the interval as 20
- 1 mark for choosing a random starting point within the first interval
- 1 mark for selecting every 20th member from the list
- 3.Calculate[3 marks]
Calculate the number from each group in a stratified sample of 30 from groups of 150, 100 and 50.
Show mark schemeHide mark scheme
Model answer
The population is 300. The groups give , and .
- 1 mark for finding the population size of 300
- 1 mark for using group size over population size multiplied by 30
- 1 mark for obtaining 15, 10 and 5
- 4.Explain[2 marks]
Explain one advantage and one disadvantage of quota sampling.
Show mark schemeHide mark scheme
Model answer
An advantage is that no sampling frame is needed, so it is quick and cheap. A disadvantage is that the interviewer chooses who to ask, so it is not random and may be biased.
- 1 mark for giving a valid advantage with a reason
- 1 mark for giving a valid disadvantage with a reason
- 5.Suggest[2 marks]
Suggest a source of bias in a survey of a town’s shoppers carried out only on Monday mornings.
Show mark schemeHide mark scheme
Model answer
People who shop on Monday mornings may differ from other shoppers, such as those who work on weekdays. Some shoppers have no chance of selection, so the sample is biased.
- 1 mark for identifying the timing as an unrepresentative selection
- 1 mark for explaining that some members have no chance of being selected
- 6.Calculate[2 marks]
Calculate an estimate of how many of 2000 customers own a pet, given that a random sample of 50 customers shows that 12 own a pet.
Show mark schemeHide mark scheme
Model answer
The sample proportion is , so the estimate is .
- 1 mark for finding the sample proportion 0.24
- 1 mark for multiplying by 2000 to obtain 480

Practice this topic
10 quick-fire multiple-choice questions, easy to hard. Tap an answer to see if you're right and the worked explanation. (The written questions with mark schemes are under “Check your recall” above.)
0 right0 of 10 answered
Includes the 2 quick checks in the note above.
EasyState[1 mark]
Show answer and explanation
Answer: D · Worked explanation
Medium[2 marks]
Show answer and explanation
Answer: C · Worked explanation
Medium[2 marks]
Show answer and explanation
Answer: B · Worked explanation
Medium[2 marks]
Show answer and explanation
Answer: A · Worked explanation
Medium[2 marks]
Show answer and explanation
Answer: D · Worked explanation
HardCompare[2 marks]
Show answer and explanation
Answer: C · Worked explanation
Hard[2 marks]
Show answer and explanation
Answer: B · Worked explanation
Hard[2 marks]
Show answer and explanation
Answer: A · Worked explanation