Welcome to the World of Sampling!
Hello! Today we are diving into one of the most practical chapters in your Unit S3: Statistics 3 course: Sampling. Have you ever wondered how TV ratings are calculated or how scientists predict election results without asking every single person in the country? They use sampling!
In this chapter, we will learn how to pick a small group (a sample) that correctly represents a much larger group (the population). Don't worry if Statistics feels a bit abstract right now—we’ll use plenty of real-world examples to make it click.
1. The Basics: Populations and Frames
Before we look at the "how," we need to understand the "what."
The Population: This is the entire group you want to study. It could be every student in your school, every lightbulb in a factory, or every person in the world.
The Sampling Unit: This is a single member of the population that could be selected. For example, if you are studying your school, one student is a sampling unit.
The Sampling Frame: This is a list of every sampling unit in the population. Imagine it as a giant register or a phone book of everyone you could possibly pick.
Did you know? Sometimes you can't have a sampling frame. For example, if you want to study the fish in the ocean, you can't exactly get a list of every single fish! In those cases, some sampling methods won't work.
Quick Review: Key Terms
• Population: The whole group.
• Sampling Unit: An individual item in the group.
• Sampling Frame: The master list of units.
2. Simple Random Sampling (SRS)
This is the "gold standard" of sampling. In Simple Random Sampling, every single member of the population has an equal chance of being selected.
How to do it:
1. Assign a unique number to every item in your sampling frame.
2. Use a random number generator (like on your calculator) or a table of random numbers to pick your sample.
Analogy: Imagine putting everyone's name into a giant hat, shaking it well, and pulling names out while blindfolded.
Pros:
• It is unbiased because everyone has the same chance.
• It is easy to do if the population is small.
Cons:
• You must have a full sampling frame (a list).
• It can be expensive and time-consuming if the population is spread out over a large area.
3. Systematic Sampling
If you want to be organized and quick, Systematic Sampling is your friend. Instead of picking random numbers for every person, you pick every \( k \)-th person.
The Process:
1. Calculate the interval \( k \): \( k = \frac{\text{Population Size (N)}}{\text{Sample Size (n)}} \).
2. Pick a random starting point between 1 and \( k \).
3. Select every \( k \)-th person after that.
Example: You have 100 students and want a sample of 20. \( k = 100 / 20 = 5 \). Pick a random number between 1 and 5 (let's say 3). You then pick student 3, 8, 13, 18, and so on.
Pros:
• Very simple and quick to execute.
• The sample is spread evenly across the list.
Cons:
• If the list has a hidden pattern (periodicity) that matches your interval \( k \), the sample will be biased. Don't worry, this is rare in exam questions, but good to know!
4. Stratified Sampling
Sometimes, your population has distinct groups, like different age groups or genders. To make sure your sample reflects these groups accurately, we use Stratified Sampling.
The Strategy:
1. Divide the population into groups called strata (e.g., Year 11, Year 12, Year 13).
2. Calculate how many people to take from each group using this formula:
\( \text{Number in sample} = \frac{\text{Number in stratum}}{\text{Number in population}} \times \text{Total sample size} \)
3. Use Simple Random Sampling within each group to pick the actual people.
Pros:
• It is the most representative method because it ensures all groups are included in the right proportions.
Cons:
• You need to know the exact sizes of the strata beforehand.
• The population must be clearly divisible into groups (you can't be in two groups at once!).
5. Quota Sampling
This is a bit different. It is non-random. This is often used by market researchers on the street.
How it works:
An interviewer is told to find, for example, 20 men and 20 women. They go out and talk to people until they have filled their "quota." If a person refuses to talk, they just move to the next person.
Analogy: It’s like a bouncer at a club who is told to let in exactly 50 people wearing blue shirts and 50 people wearing red shirts.
Pros:
• No sampling frame is needed (great if you don't have a list!).
• It is very cheap and fast.
Cons:
• Selection bias: The interviewer might only pick people who look friendly or easy to talk to.
• You can't calculate the "standard error" or use most statistical tests properly because it's not random.
Summary of Sampling Methods
Key Takeaway Table:
• Simple Random: Equal chance for all. Needs a list.
• Systematic: Every \( k \)-th person. Quick and easy.
• Stratified: Proportional groups. Most representative.
• Quota: Non-random. No list needed. Fast but biased.
Common Mistakes to Avoid
1. Confusing Stratified and Quota: Remember, Stratified uses random selection after grouping, while Quota relies on the interviewer's choice.
2. Forgetting the Formula for \( k \): Always divide the Total Population by the Sample Size, not the other way around!
3. Sampling Frame vs. Population: In the exam, if they ask for a disadvantage of SRS, always check if a list of the population actually exists. If there's no list, SRS is impossible!
Keep going! You’ve just mastered the foundations of S3 Sampling. These methods are the building blocks for the rest of the unit. Take a deep breath—you’ve got this!