Marketing Research Glossary - C

Calibration: Decision Analyst’s choice models and Conceptor® volumetric forecasting models are calibrated to category volume and brand shares. This greatly improves the accuracy of these models. Learn More

Call Disposition: A set of codes and statistics on the outcomes of telephone calls to conduct surveys.

Call Record Sheets: Telephone interviewers’ logs showing the number of dialings attempted and the results of each attempt.

Callback: An attempt to reach a person who could not be reached on the first try to interview that person, or an after-use interview for a product test.

Cannibalization: If a new product takes sales volume away from another product made by the same company, the new product is said to “cannibalize” the other product.

Canonical Analysis: An extension of multiple regression analysis that deals with two sets of dependent variables. Learn More

CAPI (Computer-Aided Personal Interviewing): Interviewer-administered surveying using a computer-based questionnaire.

Card: Also called an IBM Card. Eighty-column punched-card format, represented as a binary file. This was the standard in the research industry for many years. ASCII is now the standard.

CART (Classification And Regression Tree): An algorithm for decision-tree modeling; see Decision-Tree Models.

Cartoon Tests: Tests in which the respondent fills in the dialogue for a character in a cartoon. This is a type of projective technique.

CASI (Computer-Aided Self-Administered Interviewing): Self-administered surveying using a computer-based questionnaire.

CASRO (Council of American Survey Research Organizations): A worldwide trade organization for firms actively involved with marketing and opinion research. Decision Analyst, as a member of CASRO (, must adhere to prescribed quality standards and CASRO’s Code of Ethics. CASRO has merged with the MRA and is now referred to as the Insights Association

CASS (Coding Accuracy Support System) Certification: Approval for the accuracy of U.S. mailing addresses. CASS software ensures that mailing addresses meet the standards of the U.S. Postal Service.

Categorical Scale: A scale that asks respondents to choose from a limited number of precoded answer choices. There are three main types of categorical scales: Semantic Differential, Stapel, and Likert.

Category Usage: A question used to record if a potential respondent uses a particular product category, or not. Many studies are limited to users of a particular product category.

Cathode-Ray Tube (CRT): A computer terminal with only a keyboard and monitor (used for telephone interviewing in the marketing research industry). This term is now out-of-date and seldom used.

CATI (Computer-Aided Telephone Interviewing): Interviewer-administered telephone surveying using a computer-based questionnaire.

Causal Research: Research designed to determine whether a change in one or more variables is responsible for a change in another variable. Decision Analyst rigorously pursues the science of marketing research and the measurement of "cause and effect."

Causation: The determination that a change in one or more variables is responsible for a change in the dependent variable.

CAWI (Computer-Aided Web Interviewing): A self-administered questionnaire, presented to respondents via a webpage. A rarely-used term.

CBSA (Core-Based Statistical Area): The U.S. Census Bureau defines a “core-based statistical area” as one or more adjacent counties or county equivalents that have at least one urban center of at least 10,000 people, plus adjacent territory that has a high degree of social and economic integration with the urban core. The term “CBSA” refers to both metropolitan statistical areas and to newly-created micropolitan areas.

Cell: The individual elements (cells) that make up a sample. For example, a sample of men and women in two markets would have four sample cells: men, market one; men, market two; women, market one; women, market two. Sampling cell is very similar in meaning to a Sampling Strata. The cell is the smallest element in a sample.

Cell Assignment: The process of assigning respondents to sample cells, according to various criteria and rules.

Cell Size: The number of respondents in a sample cell. The typical sample will have many cells.

Census: A count or enumeration of every member of a population or universe.

Census Areas: Areas defined by the U.S. Census Bureau, including four census regions and nine census divisions.

Census Data: This term refers to U.S. Census data, based on an enumeration of the U.S. population every 10 years.

Census Divisions: The nine census divisions (grouping of U.S. states) are:

  • New England (Connecticut, Maine, Massachusetts, New Hampshire, Rhode Island, Vermont)
  • Middle Atlantic (New Jersey, New York, Pennsylvania)
  • South Atlantic (Delaware, Florida, District of Columbia, Georgia, Maryland, North Carolina, South Carolina, Virginia, West Virginia)
  • East South Central (Alabama, Kentucky, Mississippi, Tennessee)
  • West South Central (Arkansas, Louisiana, Oklahoma, Texas)
  • East North Central (Illinois, Indiana, Michigan, Ohio, Wisconsin)
  • West North Central (Iowa, Kansas, Minnesota, Missouri, Nebraska, North Dakota, South Dakota)
  • Mountain (Arizona, Colorado, Idaho, Montana, Nevada, New Mexico, Utah, Wyoming)
  • Pacific (Alaska, California, Hawaii, Oregon, Washington)

Census Regions: The four census regions (groupings of U.S. states) are:

  • Northeast (Connecticut, Maine, Massachusetts, New Hampshire, New Jersey, New York, Pennsylvania, Rhode Island, Vermont)
  • South (Alabama, Arkansas, Delaware, Florida, District of Columbia, Georgia, Kentucky, Louisiana, Maryland, Mississippi, North Carolina, Oklahoma, South Carolina, Tennessee, Texas, Virginia, West Virginia)
  • Midwest (Illinois, Indiana, Iowa, Kansas, Michigan, Minnesota, Missouri, Nebraska, North Dakota, Ohio, South Dakota, Wisconsin)
  • West (Alaska, Arizona, California, Colorado, Hawaii, Idaho, Montana, Nevada, New Mexico, Oregon, Utah, Washington, Wyoming)

Census Tract: An area within a zip code containing between 2,500 and 8,000 residents. These areas are defined by the U.S. Census Bureau.

Census Undercount: The percentage of the U.S. population, or the number of people, who were not counted during a U.S. Census.

Central Limit Theorem: The theorem that states for samples of size n, the distribution of sample means will converge to a normal distribution as n increases, regardless of the actual distribution of the population from which the samples are drawn.

Central-Location Study: A survey conducted at a conveniently located site (a mall, an office, a church, etc.) to which respondents are recruited to participate in a research study.

Central-Location Telephone Interviewing: A building where telephone interviewers work and from which telephone calls are made, as contrasted to interviewers calling from their homes.

Centroids: In reference to demographics: geographic points marking the approximate centers of populations within the 260,000 block groups and enumeration districts in the U.S. More generally, a centroid is the point whose coordinates are the arithmetic means of the coordinates of the points making up the figure, mass, body, population, or other entity of interest.

Certifacts: An online physician verification program used by Decision Analyst to confirm the identify and specializations of physicians in Physicians Advisory Council®, Decision Analyst's online panel of over 25,000 physicians in the U.S., Canada and Europe.

CHAID: An algorithm for decision-tree modeling; see Decision-Tree Models.

Chance Variation: In reference to unbiased sample statistics, the difference between the sample value and the true value of the population parameter.

Chat Room: An online environment where participants from different locations can interact. At Decision Analyst, we use chat rooms as an online site where focus-group participants meet to participate in real-time focus-group discussions.

Chip Game: A data-collection exercise to measure how much a respondent prefers one thing over another (e.g., products, ads, promotions). Generally, each respondent is given a fixed number of “poker chips” or “monetary chips” to allocate between two or more choices to indicate degree of preference. The more chips allocated to a choice, the more important that choice is.

Chi-Square Test: A statistical test of the goodness of fit between an observed distribution and the expected distribution of a variable.

Choice-Based Conjoint (CBC): See Choice Modeling.

Choice Modeling: Also known as Choice-Based Conjoint, it is a multivariate statistical technique that is used to simulate real-world consumer purchasing behavior. Discrete Choice and Volumetric Choice are examples of choice-modeling techniques. Learn More

ChoiceModelR™: An open-source software package written in the R-language by Decision Analyst statistical programmers. It is designed to analyze data from choice modeling experiments across a wide array of industries. Learn More

Choropleth Maps: Computer-generated maps to illustrate concentrations, densities, or patterns with various levels of shading.

Christmas Tree Pattern: A symptom of respondent fatigue or disinterest, especially in online research, when the responses for all questions in a question block are zig-zagged to look like a Christmas tree without the respondent apparently reading the question. See also Straightlining.

Churn: The percentage of panelists who leave an online research panel during a given time period. Churn is caused by changes in ISPs, new email addresses, moving to a new home, and many other reasons.

Clarifying: A “follow-up” technique for getting complete responses to open-ended questions by asking respondents to explain specific terms or words in their answers. An example of clarifying: “You indicate that you prefer the taste of Product A. What is there about the taste of Product A that you like?” A similar (but slightly different) term is Probing.

Classification And Regression Tree: See CART.

Cleaning: A series of processes and procedures to identify and eliminate “bad” data from a survey datafile, including “out of range” variables, logical inconsistencies, skip-pattern errors, etc. Decision Analyst's Tabulation Department follows a 20-point checklist to clean every study datafile. For paper questionnaires, some of the cleaning takes place during the editing process.

Click-Through Rate (CTR): The percentage of people invited to participate in an online survey that start the screener, regardless of whether or not they complete it or the survey. Similar to the term Response Rate.

Clinical Focus Groups: Focus groups that explore subconscious or unconscious motivations. Such groups can also be characterized as Motivational Research.

Closed-Ended Or Closed-End Questions: Questions that ask a respondent to choose from a list of precoded answers (e.g., “Yes” or “No;” “Excellent,” “Good,” “Fair” or “Poor;” etc.).

Cluster Analysis: Procedures for grouping objects or people into some number of mutually exclusive groups on the basis of two or more classification variables (often used to determine segments in market segmentation studies). Learn More

Cluster Sampling: Sampling approach used in door-to-door interviewing in which “clusters” are randomly selected (e.g., a sample of city blocks) to represent a larger geographic area. Cluster sampling reduces the cost of door-to-door interviewing.

CMSA (Consolidated Metropolitan Statistical Area): A cluster of primary metropolitan statistical areas (PMSAs), such as Minneapolis-St. Paul or the Dallas-Fort Worth area. CMSA markets are made up of two or more MSAs (metropolitan statistical areas).

Code: A unique number associated with each answer to a question, usually called an “answer code.” As a verb to code means to categorize answers to Open-Ended Questions. Code is also used as a reference to computer code (lines of software statements).

Code As You Go: Setting of codes at two mentions, regardless of sample size, when coding open-ended questions.

Code Of Ethics: Guidelines for making ethical decisions. For example, Decision Analyst is a member of CASRO ( and must abide by CASRO’s rigorous standards and Code of Ethics in the conduct of all marketing research projects.

Codesheet (Paper): List of codes and corresponding code numbers in ASCII or binary format for paper questionnaires.

Codebook: See Codeframe.

Codeframe: Refers to the list of codes created to summarize the responses to a question or topic. Learn More

Coding: The process of assigning numeric codes to the various responses to open-ended questions and other-specify questions.

Coefficient Of Determination (R Squared): The percent of the total variation in the dependent variable explained by the independent variables.

Cognitive Component Of Attitudes: An individual’s knowledge and assumptions about a subject or object.

Cognitive Dissonance: The psychological conflict that sometimes arises after a major purchase decision (e.g., the purchase of a car or a house). It’s the anxiety or fear that one might have made the wrong choice, and it’s too late to undo the decision. To eliminate this conflict or dissonance, the buyer will often seek to rationalize his/her choice by searching for and remembering all of the positives about the choice and ignoring all of the disadvantages.

Cohort: A group of individuals having statistical similarities in a demographic study.

Cohort Measures: Analysis over an extended time period of the activity of a cohort, a group whose members experience an event within a particular time period.

Collinearity: The correlation among independent variables. Collinearity can bias estimates of regression coefficients. Decision Analyst has developed regression-like procedures that circumvent the problems inherent in collinearity.

Column: Any vertical array of data or text. A specific space (a vertical column) on an IBM Card for recording answers to a question.

Column Binary: The system that allows more than one code (or more than one answer) to be entered into one column on an IBM Card. Column binary uses codes 0 through 9, plus X and Y. Therefore, up to 12 answers can be punched into each column.

Comparative Scales: Sets of answer choices that permit one product, brand, attribute, etc., to be compared to other products, brands, or attributes.

Competitive Benchmarking: Understanding a company's strengths and weaknesses as compared to major competitors.

Completes Per Hour (CPH): The number of interviews completed per hour of telephone interviewing (sometimes used for mall-intercept interviewing as well). Factors influencing CPH are accuracy of sample, study incidence, interview length, screener length, and cooperation rates.

Completion Rate: The percent of qualified respondents who complete the entire survey.

Completions: Questionnaires (or surveys) that are completed (i.e., all or large percentage of questions answered) and included in the final datafile for a research study.

Concentric Circles: A series of circles about a point. Generally used in retail analyses to answer questions such as “What percent of customers come from a 5-mile radius to a store? A 10-mile radius? A 20-mile radius?”

Concept (Concept Board): An illustration and description of a new product, new positioning, or new advertisement in print-ad format (usually). Learn More

Concept Description: Also referred to as Concept Statement. A brief description of a new product or service (without any pictures or illustrations). Learn More

Concept Statement: A brief written description of a new product, service, or ad. Also referred to as “concept description.” Learn More

Concept Test: A survey to measure target-market consumers’ reactions to a new product, new service, new positioning, or new advertising idea. Typical sample sizes range from 150 to 300. Learn More

ConceptCheck®: ConceptCheck® is Decision Analyst's proprietary, Internet-based system designed to flesh out and improve each new product concept. Learn More

Conceptor® Volumetric Forecasting: The results from ConceptTest®, combined with marketing plan data and target market size, can be entered into Decision Analyst’s Conceptor® models to predict a new product’s retail sales during its first year of introduction. Learn More

ConceptScreen®: Decision Analyst’s proprietary, Internet-based new product concept testing system, designed for embryonic new product concepts. ConceptScreen® identifies the ideas that are good enough to pursue. Learn More

ConceptTest®: ConceptTest® is Decision Analyst’s Internet-based system to determine the likelihood that a new product concept will succeed. ConceptTest® identifies potentially successful new products early on, so that you can focus limited research and development resources on the new product concepts with the greatest probability of consumer acceptance. Learn More

Conceptual Mapping: A moderation technique in which participants are asked to place the names of products or services on a grid. How they group the items on the diagram is used to stimulate discussion.

Conclusions: The major, overarching findings of a research study. Typically, conclusions are summarized before, and set the stage for, the recommendations in a research report.

Concomitant Variation: A predictable statistical relationship between two variables.

Concurrent Validity: The degree to which a variable, measured at the same point in time as the variable of interest, can be predicted by a measurement instrument that has been validated previously.

Conditional Probability: A probability dependent on, or influenced by, other events or circumstances. The probability that a woman is pregnant, if aged 35 to 39, is an example of a conditional probability. That is, the probability is “conditioned” by the fact that the woman must be a certain age. Another example of conditional probability is, “What is the probability of drawing an ace from a deck of cards, when two cards have already been drawn (and neither card was an ace)?” The probability of drawing an ace is “conditioned” by the number of non-ace cards already drawn.

Confidence Intervals: The range around a survey percentage, plus or minus, that is likely to contain the population parameter (the correct answer).

Confidence Level: The probability that a given statistical range or interval will include the population parameter.

Confidentiality: Confidentiality is protecting study information, such as client name, brand name, purpose of the research, concepts, products, and research results, from unauthorized disclosure to any third party. Confidentiality also refers to protecting the privacy of and preventing the identification of any individual survey respondent.

Confirmation Email: To create its double-opt-in panels, Decision Analyst sends a confirmation email to prospective panelists who have registered to become members. Only after prospective members click on these confirmation emails do they become full-fledged members of Decision Analyst’s panels. In effect, prospective panelists have to register and then confirm by email that they really do want to become members.

Confounded: Two variables are said to be confounded when the effects of one variable cannot be separated or distinguished from the effects of the other variable.

Conjoint Analysis: A multivariate statistical technique that is used to measure the relative value of product attributes. The method involves rating or ranking subsets of attribute levels, evaluated jointly, such that it forces trade-off decisions based on judgments about the value of each attribute and level. As a result, the relative utility of each level of each attribute can be computed. Choice Modeling, also known as Choice-Based Conjoint, or CBC, is a form of conjoint analysis. Learn More

Conjoint Association: A qualitative moderation technique in which participants are asked to choose between two hypothetical products or services, each with different attributes or features. The objective is to stimulate discussion about the various attributes to better understand the relative importance of each attribute.

Connection Speed: The rate at which data can be transferred over a modem or between electronic devices. See Bandwidth.

Consolidated Metropolitan Statistical Area (CMSA): A cluster of primary metropolitan statistical areas (PMSAs), such as Minneapolis-St. Paul or the Dallas- Fort Worth area. CMSA markets are made up of two or more MSAs (metropolitan statistical areas).

Constant: A value in an equation that is always the same, as contrasted with a Variable (whose value can change).

Constant Sum Scales: Scales that allow a respondent to divide up points, votes, or chips (typically 10 to 100) among two or more attributes or among two or more products to indicate relative importance.

Constitutive Definition: Statement of the meaning of the central idea or concept under study, establishing its boundaries; also known as Theoretical or Conceptual Definition.

Construct: A working hypothesis, a tentative theory.

Construct Validity: If a theoretical concept or working hypothesis (a Construct) is accurately measured by a question, scale, procedure, or device, then construct validity is achieved.

Consumer: The ultimate user of a product or service. The control of this ultimate consumer is the goal of all marketing activities and efforts.

Consumer Drawings: A projective qualitative technique often used in focus groups and depth interviews. Respondents are asked to draw pictures to represent how they feel and think about a question or topic.

Consumer Expenditure Survey (CES): An ongoing survey by the Bureau of Labor Statistics on the spending patterns of U.S. consumers.

Consumer Expenditures: The money consumers spend on goods and services.

Consumer Insights Department: See Corporate Marketing Research Departments.

Consumer Orientation: Sometimes referred to as Marketing Orientation. The notion that the consumer is at the center of the business universe, and that all business and marketing efforts must be focused on understanding and satisfying the consumer.

Consumer Packaged Goods (CPG): Consumer packaged goods is the term used in the U.S. It refers to packaged groceries, packaged beverages, packaged health and beauty products, etc. Almost all packaged products sold in supermarkets, mass merchandisers, discount chains, etc., fall within the CPG definition. Fast Moving Consumer Goods (FMCG) means the same thing and is the term used in Europe. These tend to be consumable goods, as opposed to durable goods.

Consumer Panel: Sometimes referred to as an Access Panel. A database of consumers who have agreed to take part in surveys. Typically, these consumers register and share information about their households; this information will be used in sample selection. American Consumer Opinion® Online is Decision Analyst's worldwide consumer panel with over eight million members. Learn More

Consumer Price Index (CPI): An index number used to track inflation. The Index compares the current cost of consumers purchasing a fixed set of goods and services with the cost of purchasing those same goods and services in relation to a reference year (a year in the past).

Consumer Unit: The Bureau of Labor Statistics defines a consumer unit as a consumer unit consists of any of the following: (1) all members of a particular household who are related by blood, marriage, adoption, or other legal arrangements; (2) a person living alone or sharing a household with others or living as a roomer in a private home or lodging house or in permanent living quarters in a hotel or motel, but who is financially independent; or (3) two or more persons living together who use their incomes to make joint expenditure decisions. The terms consumer unit, family, and household are often used interchangeably for convenience. However, the proper technical term for purposes of the Consumer Expenditure Survey is consumer unit.

Contact: Some type of communication with a potential respondent about participation in an upcoming survey.

Contact Rate: The percent of the total sample that was contacted (i.e., communicated with) for a survey.

Contamination: Many types of contamination pose risks to survey accuracy. The people included in the sample might not represent the sampling universe. The order of questions might contaminate answers to later questions. The information learned in testing Ad A might contaminate the respondent’s evaluation of Ad B.

Content Analysis: Another name for coding open-ended questions. A technique used to analyze respondents’ answers to open-end questions by assigning numerical codes to responses, so that all similar answers can be grouped together by tabulation software.

Content Validity: Representativeness or sampling adequacy of the measurement instrument's content.

Continuous Panel: A consumer panel in which the same respondents are sampled repeatedly for successive surveys, or in which respondents record their behavior and purchases in diaries on a continuous basis. See Diary Panels.

Continuous Variable: A quantitative variable that can assume an infinite number of values (or a large number of values) without any gaps or omissions. This variable can have a defined interval (i.e., a lower limit and an upper limit).

Contractor Advisory Board®: Decision Analyst’s international panel of general contractors and subcontractors from all segments of the building and construction industry. Learn More

Control And Test: A basic research design involving two matched samples. One sample is the control group or benchmark (the point of comparison). The second sample is the test group. The test group typically receives some type of stimulus, and both groups are then measured with the same questionnaire or instrument. Likewise, a control concept can often be included in a batch of test concepts in a dependent research design (that is, in a design which allows each respondent to see multiple concepts).

Control Cell Or Control Group: A set of respondents that receives the normal (or no) treatment and provides a basis of comparison to the test or experimental group that receives the test or experimental treatment.

Controlled Substitutions: Substituting new respondents (selected according to the same sampling criteria) for respondents in the original sample who did not respond.

Convenience Samples: Samples selected primarily for reasons of convenience (e.g., the professor who interviews students).

Convergent Validity: The degree of association among different measurement instruments (questionnaires, devices, POS systems, etc.) that purport to measure the same concept.

Cookie: Also, called an HTTP Cookie or Web Cookie. A small bit of text sent by a server and stored in a web browser. Each time the browser accesses the server, the cookie is recognized and read by the server. This enables the server to know who is entering the website, along with information about that person's past and preferences. Magic cookie, a term used in UNIX computing, is the source of the term “cookie.”

Co-Op Payment: The money or incentive given to respondents to encourage their participation in focus groups, depth interviews, mall-intercept interviews, or online surveys. Decision Analyst, for example, is one of the few research companies that pays every respondent for completing a survey a policy proven to improve the quality of online survey data.

Cooperation Rate: The percent of qualified respondents who agree to participate in a research project.

COPPA (Children’s Online Privacy Protection Act): Any website that collects information from children under the age of 13 is required to comply with Federal Trade Commission’s (FTC) Children's Online Privacy Protection Act (

Copy Testing: Another term for Advertising Testing or Advertising Research. Since newspapers and magazines were the first major advertising media, advertising research was largely the study of copy or text (hence the term Copy Testing). CopyTest® is a registered trademark of Decision Analyst and refers to its industry-leading advertising research system for the testing of television and radio commercials, print ads, and Internet ads. Learn More

CopyCheck®: Decision Analyst’s proprietary, Internet-based system to help evaluate and improve advertising concepts, early-stage print ads, TV storyboards, and radio scripts. CopyCheck® provides a directional estimate of an ad's probable effectiveness and provides insightful diagnostic feedback. Learn More

CopyScreen®: Decision Analyst’s proprietary Internet-based system to evaluate embryonic advertising concepts or ideas in a print ad format. CopyScreen® identifies the ideas that are good enough to pursue. Learn More

CopyRecall™: Decision Analyst’s proprietary, comprehensive, Internet-based, day-after advertising recall system to measure visibility and memorability of finished commercials through a real-world, on-air test. CopyRecall™ is a sound method of determining if a commercial is intrusive enough to be noticed and remembered. Learn More

CopyTest®: Decision Analyst’s proprietary, comprehensive, Internet-based advertising pretesting system to predict the effectiveness of rough to finished commercials and advertisements. Learn More

CopyTrack®: Decision Analyst’s proprietary, Internet-based advertising tracking system, composed of standard modules, for evaluating awareness and message impact of advertising in real-world environments. The data are collected via continuous, or pulsed, Internet interviews. CopyTrack® is tailored to the product category and the client's objectives, and is designed to accurately measure an advertising campaign's long-term effects. Learn More

Corporate Marketing Research Departments: Departments of major corporations that conduct, or supervise the conduct of, marketing research projects and data analyses. Sometimes referred to as Consumer Insights Department or Strategy and Insights Department.

Correlation Analysis: The measurement of the degree to which changes in one variable are correlated to, or associated with, changes in another variable. Learn More

Correspondence Analysis: A type of perceptual mapping technique. In a survey, respondents are asked to identify only the attributes that correspond with the subject of the study, then the data are used to build a perceptual map. Learn More

Counting In Questionnaires: The process of counting paper questionnaires and checking to make sure each respondent meets the required qualifications and sampling specifications.

County Size: A one-letter code (A, B, C, or D), originally created by the A. C. Nielsen Company, to indicate county size. The A counties are the largest and most urban, while the D counties are the most rural. The consolidated areas are determined by the Federal Government Office of Management and Budget. Here are more precise definitions.

  • A County: any county located in the 25 largest U.S. cities or their consolidated statistical urban areas.
  • B County: any county not designated as an A County that has a population of over 150,000 or is part of a consolidated statistical area with a population of over 150,000.
  • C County: any county or consolidated statistical area not designated as an A or B County that has population over 40,000.
  • D County: any county statistical area not designated as an A, B, or C County.

CPG (Consumer Packaged Goods): Consumer packaged goods is the term used in the U.S. It refers to packaged groceries, packaged beverages, packaged health and beauty products, etc. Almost all packaged products sold in supermarkets, mass merchandisers, discount chains, etc., fall within the CPG definition. Fast Moving Consumer Goods (FMCG) means the same thing and is the term used in Europe. These tend to be consumable goods, as opposed to durable goods.

CPH (Completes Per Hour): A term used primarily for mall-intercept and telephone interviewing. Refers to the number of completed interviews an interviewer can achieve in 60 minutes.

CPI (Consumer Price Index): The CPI is published by the Bureau of Labor Statistics and compares the prices consumers pay for a market basket of goods and services currently, versus some reference time period in the past.

CPI (Cost Per Interview): The total cost of a marketing research project divided by the total number of completed interviews.

CPM (Cost Per Thousand): A term that originated in print advertising. It means the cost of the print media advertising divided by the number of potential readers (the publication's circulation). Term is now used in radio, television, and other media.

Creative Problem Solving (CPS): A suite of creative problem-solving methods and training offered by Decision Analyst’s Innovation Team. Learn More

Criterion Variable: Also known as the Dependent Variable or Response Variable. The Criterion Variable is the variable that is being predicted or explained.

Criterion-Related Validity: The degree to which a questionnaire and/or a data set and/or a mathematical model can explain or accurately predict a criterion variable.

Critical Industry Restriction: Also known as Security Question or Security Screen. A screening question to exclude potential respondents who are employed in marketing and advertising industries, or employed in an industry directly related to the topic of the survey.

Cross-Classification Analysis: Analysis technique used with qualitative or categorical data, which classifies each respondent according to two or more mutually exclusive and exhaustive qualitative variables (such as region of residence and country of origin). Quantitative variables are sometimes used in classification analysis when transformed into categorical variables by consecutive values (such as annual income) into categories made up of ranges of values. The simplest cross-classifications are two way, but the technique can be generalized to deal with any number of dimensions.

Cross-Cultural Analysis: The collection and analysis of data that compares the findings from different countries (or cultures) together.

Cross-Elasticity: The cross elasticity of demand or cross price elasticity of demand measures the change in the number of units of one product demanded in response to a price change of a second product. The term can also be used more loosely to refer to the change in the demand for one product as the result of some change in another product. For example, the demand for new cars might go up as the price of gasoline goes down. Another example: the demand for rice might increase if the price of potatoes goes up.

Cross-validation: A process for validating the results of a predictive model by using an independent dataset.

Cross-Tabulation: Breaking out answers to questions by different groups of people (e.g., men versus women, city versus city, young versus old, Ad A versus Ad B, etc.).

Culture: The total sum of beliefs, values, and customs that make us a society. For example, culture includes the language spoken, the manner of dress, types of music, social customs, religious faith, and taboos.

Current Population Survey (CPS): A survey of 50,000 households per month conducted by the Census Bureau to track changes in population characteristics between the decennial censuses.

Custom, Or Ad Hoc, Marketing Research: Research designed to address the specific needs or problems of a given client (i.e., research custom-designed to solve a specific problem).

Customer Experience Optimization: A company strategy that maximizes long-term profitability through reaping the “lifetime value” of its customers. The goal is not to maximize customer satisfaction or customer loyalty, but rather to optimize customer satisfaction and customer loyalty. Learn More

Customer Loyalty Research: Survey research conducted to measure the loyalty (typically repeat purchases) with a product or service and related variables. Typically, these are long-term tracking studies, so that changes can be monitored over time. Related to Customer Experience Optimization and Customer Satisfaction Research. Learn More

Customer Relationship Management (CRM): A system or process that tracks all the interactions (sales, marketing, customer service, support, etc.) an organization has with customers. These systems are used to manage client relationships, measure return on investment (ROI), and data mining.

Customer Satisfaction Research: Survey research conducted to measure satisfaction with a product or service and related variables. Typically, these are long-term tracking studies, so that changes can be monitored over time. Related to Customer Loyalty Research. Learn More

Customer Value Analysis: A customer value analysis analyzes customers based on metrics such as how much they spend, how long they have been customers, etc.(i.e., how much value they add to your company.) Specifically, the analysis allows companies to know which customers are most profitable and valuable over time.

CUT (Concept-Usage Test): A European term. A concept is used to identify those interested in a product, and then the product is placed in those households for in-home usage testing.

Contact Decision Analyst

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