Marketing Research Glossary - M

Machine Cleaning Of Data: A computerized process in tabulation to clean data files before running cross-tabulations.

Machine Learning: A step towards artificial intelligence, it’s the ability for a computer program to learn from data inputs in order to make predictions.

Machine-Readable Data: Printed alphanumeric data that can be read and converted to magnetic form by an optical character reader.

Mail Panel: A group of people who have agreed to be members of a panel and to participate in mail surveys.

Mail Survey: A questionnaire administered by mail. Respondents are sent the question by mail, asked to complete it unaided, and then return the questionnaire to the research company by mail. Also called Postal Survey.

Mailers Software: A software system of mail automation tools/processes that can be used to check, clean, and correct mailing addresses, as well as conduct analyses based on demographic data.

Major Wage Earner: The member of the household who is responsible for the greatest share of the household's income.

Mall-Intercept Interviewing: Stopping (intercepting) and interviewing consumers in shopping malls.

Management Science: The application of mathematical and statistical analyses to optimize and improve the outcome of business decisions. Also known as Operations Research or Decision Analysis.

Management Summary: A brief summary of research findings, usually including recommendations, that appears in a marketing research report.

MAPPing: Mathematical Analysis of Perception and Preference. See Perceptual Mapping.

Marginal: A computer-generated frequency count of the number of people giving each answer to the questions in a questionnaire. Also called an 80-Column Dump or a Flash Report. Used primarily to double-check the results in cross-tabulations.

Marginal Report: A computer-generated table of the answers (number saying "yes," number saying "no," etc.) to each question (sometimes referred to as a Flash Report or Marginal).

Market: Total of all individuals or organizations that might buy a product or service. A market may also be a region of the country, a state, a county, a city, or some other geographic area.

Market Segmentation: The process of dividing a total market into subgroups of consumers, or potential consumers, who are similar in some way. Learn More

Market Share: The proportion (usually expressed as a percentage) of total sales of a product or service within a market.

Marketing: The process of planning and executing the distribution, pricing, promotion, advertising, and selling of goods and services.

Marketing Concept: A business philosophy based on the premise that consumers' needs and desires should be the focus of business efforts. Similar to concept of "consumer orientation" or the idea that the "consumer is king."

Marketing Decision Simulator: Also referred to as DecisionSimulator™. A computer simulation that allows clients to play “what if” games with various combinations of business and marketing variables and instantly see the results.

Marketing Information Systems (MIS): Computer systems to analyze and report sales, distribution, and marketing data.

Marketing Mix: Major marketing variables—positioning, pricing, promotion, packaging, advertising, distribution, and new product development. Learn More

Marketing Mix Modeling: Marketing mix modeling involves the use of multiple regression techniques to help predict the optimal mix of marketing variables. Regression is based on a number of inputs (or independent variables) and how these relate to an outcome (or dependent variable) such as sales or profits. Once the model is built and validated, the input variables (advertising, promotion, etc.) can be manipulated to determine the net effect on a company's sales or profits. Learn More

Marketing Optimization: The process of optimizing the direct marketing efforts for email, mail, and telephone. Learn More

Marketing Orientation: See Consumer Orientation.

Marketing Research: The identification of informational needs, the collection of relevant data, the analysis and interpretation of that data, and the reporting of that information (along with related recommendations) to senior management to improve decision making related to marketing. The tools and techniques of marketing research can also be applied to solve a wide range of business problems unrelated to marketing. Learn More

Marketing Research Aggregator: A company that acquires, catalogs, reformats, segments, and resells reports already published by large and small marketing research firms.

Marketing Research Objective: A goal statement specifying the type of information needed by the decision maker to help solve the management decision problem and the way in which that information can be obtained efficiently and effectively.

Marketing Research Problem: A statement specifying the type of information needed by the decision maker to help solve the management decision problem.

Marketing Science: Marketing science is the application of the scientific method and scientific experiments to the solution of marketing problems. Learn More

Marketing Strategy: The foundational strategy that helps a company survive and thrive long-term. Marketing strategy must address the following variables: positioning, pricing, advertising, distribution, promotion, sales, product improvements, and new products. Strategy should rarely change, once it is fully proven and validated via marketing research. Learn More

Marking Off: The process of marking off question numbers on the front of a paper questionnaire to record the open-ended questions that have been coded.

Markov Chain Analysis: Analysis based on the assumptions of a Markov Chain process, a stochastic process in which a discrete random variable can change value at specified times, with the new value depending only on the present value and not on previous history. Used to calculate the probability of an occurrence of an event. For example, the analysis of brand switching to predict brand shares in future time periods is an application of the Markov process.

Maturation: Changes in experimental subjects that take place during an experiment that may affect their responses to the experimental variables.

MaxDiff: A form of conjoint analysis where survey respondents are shown a subset of the possible items and are asked to indicate the two elements of the subset that represent the maximum difference (MaxDiff); e.g., most favored and least favored, or most and least important, or most and least appealing, etc. MaxDiff forces respondents to make choices between options, which in turn provides rankings showing relative importance to researchers of each item. Learn More

Mean: The sum of the values for all measurements or observations of a variable divided by the number of observations (same meaning as Average).

Mean Square Error: The average of the squared differences between actual and predicted values of a variable. It is a measure of the total error to be expected for a sample estimate.

Measure Of Location: A quantity that locates a particular position in a frequency distribution. The mean, for example, is one measure of the center of a frequency distribution.

Measurement: The process of assigning numerical quantities (or labels) to things (age, number of purchases, dollars spent, visits to store, attitudes, preferences, etc.) in accordance with specific rules to represent quantities or qualities of marketing variables. See Observation.

Measurement Error: The error that results from the difference between the information sought and the information actually obtained by the measurement process.

Measurement Instrument Bias: The error that results from the design of the questionnaire or measurement instrument.

Media Marketing Areas: The two firms that measure TV audiences, Arbitron and Nielsen, have slightly different definitions of media marketing areas (i.e., television markets). Arbitron's TV markets are called Areas of Dominant Influence (ADIs), while Nielsen's are Designated Market Areas or DMAs.

Media Segmentation: A type of segmentation that is based on the fact that different media tend to reach different audiences. If a brand pours its entire budget into one medium, it can possibly dominate the segment of the market that, for example, listens to a particular radio station or reads a particular magazine. Learn More

Median: The middle number in an ascending or descending array of numbers. If the number of numbers is even, then the median is an average of the two middle numbers.

Memory: The record of past events, emotions, and perceptions stored in the human mind. Term also used to refer to the part of a computer that stores information or instructions.

MenuAudit™: MenuAudit™ is a system to evaluate the quality and appeal of each item on a restaurant's menu.

Metadata: Data about data. For example, during a survey, the software might record length of interview, time spent answering each question, changes to answers, etc. These are examples of metadata.

Metaphor Technique: See Storytelling.

Methodological Log: A journal of detailed and time-sequenced notes on the investigative techniques used during an inquiry, with special attention to biases or distortions a given technique may have introduced.

Methodology: The specific steps followed to conduct a marketing research project. Also, the section of the final report in which the researcher outlines the methods used in the research, including target sample, sampling source and method of selection, the method of recruiting participants, the types of questions used, number and type of interviews, and so on.

Metric Scale: Measurement system in which all three of the following are true: observations can be ranked from smallest to largest, the distance between observations is meaningful, and the ratios among the observations are meaningful. Also known as Ratio Scale.

Metropolitan Division: Metropolitan division refers to a county or group of closely-related contiguous counties that serve as a distinct employment region within a Metropolitan Statistical Area that has a population core of at least 2.5 million. While a metropolitan division is a subdivision of a larger metropolitan statistical area, it often functions as a distinct social, economic, and cultural area within the larger region. This is a new classification as of June 2003.

Microdata: Census records of individual respondents stripped of their identifying information. Census microdata are available as public-use microdata samples (PUMS).

Micropolitan Statistical Area: The U.S. Census Bureau defines "micropolitan statistical area" as having an urban core population of at least 10,000 but less than 50,000. The micropolitan area designation was created in 2003.

Migration: Movement of people from one geographic area to another.

Minigroup: A focus group that contains four to six participants. More than six is normally considered a full group, and fewer than four is a triad or a dyad.

Mixed Groups: A focus group that contains both males and females.

Mobility: The ability of a group of people or individual to travel or move.

Mode: The value in an array of numbers that occurs most frequently.

Modeling: The use of mathematical variables and equations to simulate a business process, marketing process, or consumer decision process.

Moderator: The person who leads and facilitates a focus group (or group discussion). The moderator should be almost invisible to the group discussion process and should lead the discussion in a reflective, nondirective manner. The overactive, aggressive, "machine-gun the respondents with constant questions and probes" moderator introduces significant bias into a group discussion. All of Decision Analyst's moderators are trained in Rogerian reflective techniques and other nondirective methods. Moderator is sometimes used as title of someone conducting depth interviews, also.

Moderator Guide: Also called Discussion Outline or Discussion Guide. The outline of topics that a moderator uses as a roadmap to guide a focus group discussion. Decision Analyst's moderators develop the discussion outline after a detailed alignment meeting with the Client. The discussion outline is designed to provide information that will help solve marketing problems and/or help identify marketing opportunities. A moderator guide is just that, a guide. The moderator will often need to deviate from the moderator guide as new information is discovered.

Monadic: A research design in which each respondent evaluates only one thing (e.g., one product or one advertisement or one package). Learn More

Monitor or Monitoring: A quality-control process in which a second person observes and/or listens to a telephone or in-person interview to ensure that required procedures are followed.

Monte Carlo Simulations: A technique that helps to reduce the uncertainty in estimating future outcomes. This method is a stochastic technique—meaning it relies on repeated random sampling to investigate problems. Monte Carlo simulation is applied to complex, nonlinear models or those that involve more than just a couple of uncertain parameters. It is useful in risk management, project planning, cost modeling, economic studies, strategic planning, etc.

Mortality: The loss of test units or subjects during an experiment or long-term research study.

Motivational Research: Research designed to measure or reveal underlying motives (unconscious or subconscious) for human behavior. Depth interviews and focus groups are the primary techniques for motivational research, with an emphasis on the use of projective techniques to reveal hidden motives. Ethnographic investigations (or observational research) are also widely used as motivational research techniques. Learn More

Moving Average: The mean of a series of measurements drawn over time. Moving averages are used to remove fluctuations of data.

MRA: The Marketing Research Association. This U.S. based professional organization focuses upon data collection and field services. In 2017, the MRA has merged with CASRO to become the Insights Association.

MRD: Marketing Research Department, typically in a large corporation.

MRS: The Market Research Society (based in the UK ). A professional society for those who are involved in or concerned with marketing and opinion research.

MSA (Metropolitan Statistical Area): A freestanding metropolitan area surrounded by nonmetropolitan counties and not closely associated with other metropolitan areas. Each MSA is grouped by population size and coded using government FIP codes. A metropolitan statistical area containing an urbanized area of at least 2.5 million people can be subdivided into two or more Metropolitan Divisions, provided specified criteria are met.

Mugging: Marketing under the guise of marketing research. Selling under the guise of marketing research is called Sugging.

Multichotomous Question: Same as a Multiple-Choice Question. A closed-ended question that asks the respondents to choose among several answers.

Multicollinearity: In multivariate analyses, some of the independent variables may be correlated with each other. This condition is referred to as multicollinearity.

Multidimensional Scaling (MDS): Procedures designed to measure several dimensions of a concept or object (often used in brand image and brand equity research).

Multinomial Logit Model: A version of regression analysis using a specific S-shaped curve (the logistic curve) instead of a straight line. Used to model probability of an outcome when outcome variables are binary (e.g., yes/no rather than continuous numbers). Also known as a Logit Model

Multiple-Choice Question: A question with more than two predetermined answer choices. A question with the answer choices Excellent, Good, Fair, and Poor would be an example of a multiple-choice question.

Multiple-Discriminant Analysis: A statistical technique for predicting group membership (e.g., product user versus nonuser) on the basis of two or more independent variables.

Multiple Regression Analysis: A statistical technique for explaining or predicting a dependent variable based on multiple independent variables. Learn More

Multiple-Response Grid: A question type that allows for multiple responses per row and multiple responses per column. See example below:

 

Multiple-Response Question: A closed-ended question that allows a respondent to choose more than one answer choice. See example below:

 

Multiple Time-Series Design: An interrupted time-series design with a control group. Learn More

Multivariate Analysis: Statistical techniques that simultaneously analyze the influence of multiple variables. Learn More

Multivariate Analysis Of Variance (MANOVA): A statistical analysis used to assess the significance of the effect of one or more independent variables on two or more dependent variables. Usually used when outcome measures (dependent variables) are thought to be intercorrelated. Learn More

Multivariate Regression Analysis: See Multiple Regression Analysis.

Mutually Exclusive: Two items or two groups are said to be mutually exclusive if there is no overlap between the two items or two groups.

Mystery Shoppers: People employed to pose as typical consumers and shop at retail stores or other businesses to measure service levels and business performance.

Contact Decision Analyst

If you would like more information on Marketing Research, please contact Jerry W. Thomas by emailing jthomas@decisionanalyst.com or calling 1-817-640-6166.