Welcome to Statistical Sampling!
Ever wondered how news channels predict election results before all the votes are counted? Or how scientists know a new medicine works without testing it on every single person on Earth? The answer is Statistical Sampling.
In this chapter, we are going to learn how to pick a small group of people (or things) to represent a much larger group. This is a vital skill in Statistics because, in the real world, we rarely have the time or money to ask everyone everything. Don't worry if some of the terms sound a bit "maths-heavy" at first—we’ll break them down using simple examples like soup and shopping!
1. The Big Picture: Population vs. Sample
Before we can start picking groups, we need to know what we are picking from and why.
Key Terms
- Population: The entire group of items or people that you are interested in. Example: Every student in your school.
- Sample: A smaller group picked from the population to represent them. Example: 20 students picked from the canteen at lunch.
- Census: When you collect data from every single member of the population.
The "Soup" Analogy
Imagine you are cooking a massive pot of vegetable soup. You want to know if it needs more salt. You don't drink the whole pot (that’s a Census). Instead, you stir it well and take one spoonful (that’s a Sample). If that spoonful tastes salty, you infer that the whole pot is salty.
Did you know?
The UK government carries out a Census every 10 years. It is a massive job that tries to reach every single person living in the country!
Quick Review: If you want to know the average height of trees in a forest, the "Population" is all the trees, and the "Sample" is the specific 50 trees you actually measure.
2. Making Inferences
The whole point of a sample is to make an inference. This is just a fancy word for "making an educated guess about the population based on your sample."
If your sample is "representative" (meaning it looks like a mini-version of the population), your guess will be good. If your sample is biased (it doesn't represent the group well), your guess will be wrong.
Example: If you only ask the school basketball team about their height, you might "infer" that every student in the school is 6 feet tall. That is a biased sample!
3. Sampling Techniques: Things you need to DO
The OCR syllabus requires you to understand and be able to use these two specific methods:
A. Simple Random Sampling
In this method, every member of the population has an equal chance of being picked. It’s like putting everyone’s name into a giant hat and pulling them out.
How to do it:
- Assign a unique number to every member of the population.
- Use a random number generator (on your calculator or a computer) to pick numbers.
- Match those numbers back to the people/items.
The Pro: It is completely fair and removes bias.
The Con: It can be difficult and time-consuming if the population is very large (imagine giving a number to every person in London!).
B. Opportunity Sampling (Convenience Sampling)
This is simply picking people who are available at the time and fit your criteria. Example: Standing outside a supermarket and asking the first 10 people who walk past.
The Pro: It is very easy, quick, and cheap.
The Con: It is highly likely to be biased. You only meet the people who happened to be there at that specific time.
Key Takeaway: Random is fair but hard; Opportunity is easy but biased.
4. Sampling Techniques: Things you need to CRITIQUE
For these methods, you don't need to do the calculations, but you must be able to explain what they are and why they might be good or bad in a specific situation.
A. Systematic Sampling
Choosing items at regular intervals from a list. Example: Picking every 10th person on a school register.
- Critique: It's quick, but if there is a hidden pattern in the list, it could be biased.
B. Stratified Sampling
The population is divided into groups (strata) based on a characteristic (like age or gender), and then a random sample is taken from each group in proportion to the size of the group.
- Critique: This is the "Gold Standard." It ensures every sub-group is represented fairly. However, it's complex because you need to know the exact makeup of the population beforehand.
C. Quota Sampling
Similar to stratified, but the researcher is told to find a specific number of people in certain groups. Example: "Go find 20 men and 20 women to interview."
- Critique: Once the researcher finds their 20 men, they stop asking men. This is often used in street market research. It's fast, but not truly random because the researcher chooses who to talk to.
D. Cluster Sampling
The population is divided into "clusters" (usually based on location), and then one or more clusters are chosen at random to be studied entirely. Example: To study UK students, you randomly pick 5 schools and interview everyone in them.
- Critique: Much cheaper than traveling all over the country, but the clusters might not represent the whole population (e.g., a school in a wealthy area won't represent all UK schools).
5. Common Pitfalls and Critique Skills
In your exam, you might be asked to "critique" a sampling method. Here is what to look out for:
Variation (Sampling Error)
Important Point: Different samples will lead to different conclusions about the population. This is natural! Even if you use perfect random sampling, two different groups of 50 students will give slightly different average heights. This is called Sampling Variation.
Common Mistakes to Avoid:
- Confusing Census and Sample: Remember, a Census is everyone; a Sample is a part.
- Ignoring Bias: Always check if the method excludes a certain group. (e.g., "They only sampled people with landline phones—this excludes younger people!").
- Sample Size: If a sample is too small (e.g., asking only 2 people), the results are not reliable.
Memory Aid: The "S" Methods
If you're struggling to remember the names, think of the 4 S's:
1. Simple Random (The Hat)
2. Systematic (The Every-10th)
3. Stratified (The Proportions)
4. Sample (The small group)
6. Summary Table for Revision
Method: Simple Random
Best for: Fairness and avoiding bias.
Method: Opportunity
Best for: Speed and low budget.
Method: Stratified
Best for: Ensuring small groups in the population are represented.
Method: Quota
Best for: Fast, targeted market research.
Final Encouragement: Statistics is about more than just numbers—it's about telling a story. When you look at a sampling question, ask yourself: "Is this story fair to everyone in the population?" If you can answer that, you’re already halfway to an A!