In statistics, a population is the set of all entities that we are interested in learning something about. These ‘entities’ could literally be anything, including people, households, countries, chemical reactions, species, planets, years in history, etc. We are typically interested in answering some question about the population: how many days last year did it snow?, what proportion of people are overweight?, how many households earn more than $100,000 per year?
Generally, however, it is not possible or feasible to make measurements of every member of the population. For example, if a business wanted to know how many people would buy a certain new product, it would not be possible for them to ask literally every person in the country. Even in simpler cases, such as a school that wished to know how its students traveled to school in the morning, it might be infeasible to collect information from the entire school population. Instead, statistical analysis proceeds by collecting data from a small subset of the population known as a sample. The data from the sample is analysed, and on the basis of the results of this analysis inferences are made about the entire population. This process is known as statistical inference.
What is the difference between a population and a sample?: A simple and concise explanation of the difference
Populations and samples: A discussion of the relationship between populations and samples, with examples
Statistics without tears – populations and samples: A detailed introduction to populations, samples, and sampling methods from a journal article