Reference

Glossary of market research terms

34 common terms, explained in plain English. Each entry has its own link, so you can point a classmate or colleague straight to it.

A

Acquiescence bias #: The tendency of respondents to agree with statements regardless of their content, especially in long lists of agree/disagree items.

Bottom-up estimate #: A market size estimate built from things you can count, such as reachable customers, how often they buy and what they pay.

Closed question #: A question with a fixed set of answer options, such as yes/no, multiple choice or a rating scale. Easy to count, but limits what people can say.
Cluster sampling #: Randomly selecting whole groups, such as housing societies, schools or villages, and then surveying people within the chosen groups.
Confidence level #: How sure you can be that the true figure lies within your margin of error if you repeated the survey many times. 95% is a common choice.
Convenience sample #: A sample made up of whoever is easiest to reach. Useful for early exploration, but the results may not represent the wider population.

Discussion guide #: The planned outline of topics and questions for an interview or focus group. A guide to follow flexibly, not a script to read aloud.
Double-barrelled question #: A question that asks about two things at once, such as “Was the food tasty and affordable?”, making an honest single answer impossible.

Focus group #: A moderated discussion with a small group of people, used to explore reactions, opinions and the reasons behind them.

Leading question #: A question worded in a way that nudges people towards a particular answer, for example by assuming they liked something.
Likert scale #: A rating scale, usually five or seven points, running from one extreme to the other, such as “strongly disagree” to “strongly agree”.

Margin of error #: The likely range around a survey result within which the true figure falls, at a given confidence level. Smaller samples have wider margins.
Mystery shopping #: Visiting or buying from a business as an ordinary customer to observe service, prices and experience first-hand.

Non-response bias #: Distortion that arises when the people who do not respond differ in important ways from those who do.

Open question #: A question people answer in their own words, such as “What nearly stopped you from buying?” Rich in detail, slower to analyse.

Pilot test #: A small trial run of a survey or interview guide with a few people, to find confusing questions and technical problems before the real launch.
Population #: The whole group of people or organisations you want to learn about, for example every household within your delivery area.
Primary research #: Research where you collect new information yourself, through surveys, interviews, observation or experiments.

Qualitative research #: Research that explores reasons, feelings and experiences in words, typically through interviews, focus groups or observation.
Quantitative research #: Research that measures things in numbers, such as how many people do something or how strongly they rate it, typically through surveys.
Quota sampling #: Recruiting until fixed numbers of people from set groups have taken part. Gives some balance but is not random.

Random sample #: A sample in which every member of the sampling frame has a known, usually equal, chance of being chosen.
Response rate #: The share of people invited to take part who actually complete the survey or interview.

Sample #: The subset of the population that you actually collect information from.
Sampling frame #: The list or source from which a sample is drawn, such as a customer register or a set of locations. Gaps in the frame become gaps in the results.
Screener #: A short set of questions used to check whether a potential participant fits the profile you need before inviting them to an interview or group.
Secondary research #: Using information that already exists, such as published reports, government data, websites or reviews, rather than collecting it yourself.
Serviceable addressable market (SAM) #: The part of the total market that your business can actually serve, given its location, product, price and channels.
Serviceable obtainable market (SOM) #: The share of your serviceable market that you can realistically win within a given period, considering competition and capacity.
Social desirability bias #: The tendency of people to give answers that make them look good, rather than answers that reflect what they really do or think.
Stratified sampling #: Dividing a population into groups, such as age bands or areas, and drawing a random sample from each group.

Top-down estimate #: A market size estimate that starts with a large total, such as a population, and narrows it with a series of percentage assumptions.
Total addressable market (TAM) #: The total demand for a type of product or service if every possible customer bought it. The outer boundary of a market estimate.
Triangulation #: Checking a finding by comparing results from different methods or sources, such as a survey, interviews and sales records.

Want to see these ideas in action? Start with the guides.