Statistics for Everyday Life
Population vs Sample
Almost all statistics rests on this distinction: you rarely measure everyone, so you measure some and reason about the rest. Getting it straight is the foundation of reading any study.
| Aspect | Population | Sample |
|---|---|---|
| What it is | The entire group you want to know about | A subset of the population that you measure |
| Size | Often huge, or impossible to measure fully | Manageable — as small as a few hundred can work |
| Numbers are called | Parameters (e.g. the true mean, μ) | Statistics (e.g. the sample mean, x̄) |
| Role | What you want to conclude about | The evidence you use to infer it |
| Key risk | — | Sampling error and bias if it is unrepresentative |
When to use population
Work with the whole population when it is small enough to measure completely — a class of 30, a company’s own employees.
When to use sample
Use a sample when the population is too large or costly to measure in full, and draw it randomly so it represents the whole.
Frequently asked questions
- What is the difference between a population and a sample?
- The population is everyone or everything you want to draw a conclusion about; the sample is the smaller group you actually measure. You use the sample to estimate what is true of the population.
- Why sample instead of measuring the whole population?
- Because measuring everyone is usually impossible, slow, or expensive. A well-drawn random sample of a few hundred can estimate a population of millions surprisingly well — what matters is representativeness, not the fraction measured.
- What is sampling error?
- The natural gap between a sample’s result and the true population value, simply because you measured a subset. It shrinks with larger samples — but no sample size fixes a biased, unrepresentative sample.