Sample and Population

In statistics and research design, a population is the entire group you wish to understand, while a sample is a smaller subset drawn from it for study. The relationship between them is fundamental: you rarely study everyone, so you examine a carefully chosen few to make inferences about the whole.

A population might be "all voters in a country" or "every star in a galaxy"—sometimes finite, sometimes conceptually infinite. A sample is what you actually measure: perhaps 1,000 randomly selected voters, or observations of 500 stars. The quality of your conclusions depends entirely on whether your sample truly represents the population, a challenge addressed by sampling theory.

The gap between sample and population creates both opportunity and peril. A well-designed sample can reveal truths about millions with elegant efficiency. A biased sample—surveying only people near a subway station, or observing only visible stars—can mislead catastrophically. This tension drives careful thinking about variables, systematic selection, and recognizing when your sample might not reflect reality.

Understanding this distinction transforms how you read studies, interpret polls, and think about what's knowable.

Related

Statistics, Bias (statistics), Sampling, Inference, Survey design, Data collection