The term survey refers to various types of observation, or techniques of observation, including questionnaires that are used to measure the characteristics/attitudes of a group of people, public opinion polls, market research surveys, and more. Surveys provide all sorts of important information such as public information (census) and data for various fields of research (psychology, marketing, etc.).

The purpose of a survey is to obtain a random sample of a population in order to draw conclusions or make statistical inferences about the characteristics of the population being studied. Surveys are often performed because it is usually too expensive or too difficult to obtain data from the entire population being studied. As long as proper random sampling procedures are used, the sample obtained from a survey should be representative of the population, and valid inferences about the population can be made, granted that there will always be some degree of error. This is because, by definition, a sample is always a part of a population, so the sample cannot fully represent the population, leading to a discrepancy between the real (unknown) population parameter and that predicted using the sample.

Survey methodology

Survey methodology is a scientific field of its own that seeks to analyze the aspects of surveying (sample design, data collection procedures, data processing, data analysis, etc.) that can result in systematic and random survey errors. Because statistical inferences are made based on the samples obtained through surveying, errors that result based on survey methodology have the potential to invalidate said inferences. Below are examples of some areas survey methodologists must pay particular attention to:

Surveys vs experiments

Surveys and experiments are both techniques used as part of inferential statistics. A survey involves the use of a random sample of the population, rather than the whole, with the goal that all subjects in the population have an equal chance of being selected. The random sample of the population is then used to draw conclusions or make inferences about the population as a whole.

In contrast, an experiment typically involves the use of random assignment such that all subjects have an equal chance of being assigned to the groups (treatment and control) in the study, which minimizes potential biases, as well as allows the experimenters to evaluate the role of variability in the experiment. This in turn allows them to determine whether any observed differences between the groups merit further study or not based on whether or not the differences can be attributed to variability or chance.