Population vs Sample
Big Idea: Population = ALL individuals of interest. Sample = a subset (smaller group) from the population.
| Term | Definition | Example |
|---|---|---|
| Population | All units you want to study | All 10,000 students in a school district |
| Sample | Subset from the population | 500 students chosen from the district |
Why sample?: Populations are often huge or impossible to access.
A good sample gives reliable results at lower cost.
Free preview
This is the free notes preview
You're reading the free notes. Aimnova Pro unlocks the full study experience — and you can try it with your first topic free to keep:
- FlashcardsLock in vocabulary and key terms with spaced repetition.
- Practice questionsAnswer exam-style questions and get instant AI marking.
- Mock exams & past-paper vaultSit full mocks and see exactly how examiners award marks.
- Personalised study planA daily plan built around your exam date and weak areas.
Random vs Non-random sampling
Random sampling: Each individual in population has an equal chance of selection.
Removes selection bias.
Non-random sampling: Individuals are selected deliberately (e.g., easiest to reach).
Can introduce bias.
| Method | How it works | Bias risk |
|---|---|---|
| Simple random | Random number generator or names drawn from a hat | Low bias |
| Systematic | Random start, then every k-th member of an ordered list | Can be biased if the list has a pattern |
| Stratified | Divide into groups, random sample from each in proportion | Low bias |
| Quota | Target number from each group, filled with whoever is available | Bias risk: not random inside groups |
| Convenience | Select the easiest or nearest individuals | HIGH BIAS |
IB-style question — name the sampling technique
A factory lists all 2000 items in production order. An inspector checks every 25th item on the list.
(a) Name this sampling technique. (b) Name the technique if instead the inspector just grabs the 30 items nearest the door.
Step by step
- (a) Choosing every kth item from an ordered list is SYSTEMATIC sampling.
- (b) Taking whatever is easiest to reach is CONVENIENCE sampling (and is likely biased).
Final answer
(a) systematic. (b) convenience (biased).
Never wonder what to study next
Get a personalized daily plan based on your exam date, progress, and weak areas. We'll tell you exactly what to review each day.
Simple Random Sampling
Worked example — select a random sample
A school has 800 students.
We need a sample of 50 using simple random sampling.
Describe the method.
Solution
- Label each student with a number from 001 to 800 (3 digits for consistency).
- Use a random number generator (or table) to generate 50 different numbers between 001 and 800.
- Select the students with those numbers.
Final answer
This ensures every student has equal 1/800 chance of selection, eliminating selection bias.
In exam: You may be asked to: (1) describe the method, (2) explain why it's better than convenience sampling, (3) implement it using random numbers.
Stratified Sampling
When to use: Use stratified sampling when the population has distinct groups (strata) that differ from each other.
Worked example — stratified sampling
A school has: 200 Year 9, 250 Year 10, 180 Year 11.
Sample 50 students using stratified sampling by year.
Solution
- Total population = 200 + 250 + 180 = 630
- Calculate proportion per stratum: Year 9: 200/630 = 0.317 Year 10: 250/630 = 0.397 Year 11: 180/630 = 0.286
- Apply proportions to sample size (50): Year 9: 0.317 × 50 ≈ 16 students Year 10: 0.397 × 50 ≈ 20 students Year 11: 0.286 × 50 ≈ 14 students
- Randomly select 16 Year 9, 20 Year 10, 14 Year 11.
Final answer
Sample of 50 now reflects year-group proportions of the population.
Stop wasting time on topics you know
Our AI identifies your weak areas and focuses your study time where it matters. No more overstudying easy topics.
The five methods in the guide: Simple random: every member has the same chance (random numbers, names from a hat). Systematic: an ordered list, a random start, then every k-th member. Stratified: split into groups, a random sample from each group in proportion to its size. Quota: a target number from each group, filled with whoever is available. Convenience: whoever is easiest to reach.
See it drawn, step by step
In My Learning, handwritten diagrams build one step at a time. Play, pause and replay each explanation until it clicks. Create your free account to try it.
Worked example — a member list
A swimming club has an alphabetical list of 720 members. The secretary wants a systematic sample of 40.
(a) Find the sampling interval.
(b) The random start is 11. Write down the first three members chosen.
Step by step
- (a) Population size over sample size.
- (b) Start at 11 and add 18 each time.
Final answer
(a) k = 18 (b) members 11, 29 and 47
Why the start is random: Without a random start the same positions are always chosen. If the list has a pattern every k places, the sample can be biased.
See how examiners mark answers
Answer exam-style questions with model answers. Learn exactly what earns marks and what doesn't.
Say who is missing: A disadvantage answer earns its mark when it says how the sample may not represent the population, in the story: "only Monday-morning customers are asked", not just "it is biased".
Exam-style question — a gym survey [4 marks]
A gym has 400 members: 240 adults and 160 students. The owner wants members’ views on new opening hours. She asks the first 10 adults and the first 10 students who come in on Saturday morning.
(a) State the sampling method the owner used. [1]
(b) State one reason why this method may lead to an invalid conclusion. [1]
(c) She decides instead to take a stratified sample of 30 members. Find how many adults and how many students should be in it. [2]
Step by step
- (a) A set number from each group, whoever comes in.
- (b) Who is missing?
- (c) Each group’s share of the sample.
Final answer
(a) quota (b) the sample may not represent all members (only Saturday-morning visitors) (c) 18 adults and 12 students
To get full marks
- Name the method in one or two words.
- A disadvantage in context: who is missing.
- Stratified shares add up to the sample size (18 + 12 = 30).