What Is Population?

In statistics, a population is the pool from which a sample is drawn for a study. Thus, any selection grouped by a common feature can be considered a population. A sample is a statistically significant portion of a population.

Understanding Populations

Statisticians, scientists, and analysts prefer to know the characteristics of every entity in a population to draw the most precise conclusions possible. However, this is impossible or impractical most of the time since population sets tend to be quite large. A sample of a population must usually be taken since the characteristics of every individual in a population cannot be measured due to constraints of time, resources, and accessibility.

For example, there is no real way to gather data on all of the great white sharks in the ocean (a population) because finding and tagging each one isn't feasible. So, marine biologists tag the great whites they can (a sample) and begin collecting information on them to make inferences about the entire population of great whites. This is a random sampling approach because the initial encounters with tagged great whites are entirely random.

A valid statistic may be drawn from either a sample or a study of an entire population. The objective of a random sample is to avoid bias in the results. A sample is random if every member of the whole population has an equal chance to be selected to participate.

How to Measure a Population

The difficulty of measuring a population lies in whatever you're attempting to analyze and what you're trying to accomplish. Data must be collected through surveys, measurements, observation, or other methods. Therefore, gathering the data on a large population is generally not done because of the costs, time, and resources necessary to obtain it. For instance, when you see advertisements claiming, "62% of doctors recommend XYZ for their patients,"—all of the doctors with patients who could use XYZ in the U.S. were likely not contacted. Of the doctors who responded to the several hundred or thousand surveys that were requested, 62% responded that they would recommend XYZ—this is a population sample.

Population and Investing

While a parameter is a characteristic of a population, a statistic is a characteristic of a sample, and samples can only result in inferences about a population characteristic. Inferential statistics enables you to make an educated guess about a population parameter based on a statistic computed from a sample randomly drawn from that population.

Statistics such as averages (means) and standard deviations, when taken from populations, are referred to as population parameters. Many, such as a population's mean and standard deviation, are represented by Greek letters like µ (mu) and σ (sigma). Much of the time, these statistics are inferential in nature because samples are used rather than populations.

Market and investment analysts use statistics to analyze investment data and make inferences about the market, a specific investment, or an index. In some cases, financial analysts can evaluate an entire population because price data has been recorded for decades. For example, the price of every publicly traded stock could be analyzed for a total market evaluation because the prices are recorded—this is a population, in terms of investment analysis. Another population might be the stock prices of all tech companies since 2010. An analyst can calculate parameters with all of this data; however, the parameters used by analysts are only occasionally used in the same way statisticians and scientists use them. Some of the parameters you might see used by investment analysts, statisticians, and scientists and their differences are:

The Bottom Line

In statistics, a population is the pool being studied from which data is extracted. Populations can be difficult to gather data on, especially if the studied topic is expansive and widely dispersed. Studying humans is an excellent example—there is no way to gather data on every brown-eyed person in the world (a statistical population), so random sampling is the only way to infer anything about that population. In investment analysis, populations are generally specific types of assets being analyzed. These data sets are generally small (in statistical terms) and easy to acquire because they have been recorded, unlike data on living organisms, which is much more difficult to obtain.