Simple Random Sampling
What you'll learn: How to select samples where every individual in the population has an equal chance of being chosen.
The Core Idea
Simple Random Sampling (SRS) is the fairest, most straightforward way to draw a sample from a population. In SRS, every individual has the exact same probability of selection, and every possible combination of individuals (of the given sample size) is equally likely.
Think of it like drawing names from a hat: you mix up all the names thoroughly, close your eyes, and pick without peeking. Each name has the same chance of being drawn.
Why It Matters
Simple random sampling is the gold standard for creating representative samples. Because selection is completely random, you avoid bias—you're not favoring certain groups or patterns. This makes your sample statistics (like the sample mean) reliable estimates of population parameters (like the population mean).
How It Works in Practice
- Define your population clearly (e.g., all 10,000 customers)
- Assign each individual a unique identifier (numbers 1 through 10,000)
- Use a random mechanism to select your sample (random number generator, lottery-style draw)
- Every selection is independent—picking one individual doesn't affect who else gets picked
Analogy
Imagine a lottery machine with numbered balls. If you want a sample of 100 from 10,000 people, you put 10,000 balls in the machine, spin thoroughly, and draw 100 balls. No ball is more likely than another—that's simple random sampling.
Key Takeaway: Simple random sampling gives every individual an equal probability of selection, creating unbiased, representative samples that form the foundation for reliable statistical inference.