A

AAU (attitude, awareness and usage) study
A type of tracking study that monitors changes in customer attitudes, awareness and usage levels for a product category or specific brand.

Accuracy
The degree of conformity of a sample statistic to the population.

Active buyer
Customer whose latest purchase was made within the last 12 months.

Ad concept testing
Testing used to determine the target audience reaction to alternative advertising approaches or preliminary ad concepts.

Ad hoc surveys
Questionnaires administered to the target audience with no prior contact by the researcher.

Ad positioning statement tests
Testing to determine reactions of the target audience to positioning statements that are being considered for use in advertisements.

Ad tracking research
Periodic measurements of the impact of advertisements over time.

Allowable sample error
The amount of sampling error the researcher is willing to accept.

Applied research
Any research which is used to answer a specific question, determine why something failed or succeeded, solve a specific, pragmatic problem, or to gain better understanding.

Array
A report on a value field with frequency distribution given for specific values.

ASCII (American standard code of information interchange)
Widely used code for transmission of data from one database to another.

Average
The sum of the values for all observations of a variable divided by the number of observations. Also called mean.

Awareness
The proportion of people who are familiar with a product, brand name or trademark.

B

Balanced scales
Scales with the same number of positive and negative categories.

Banner
The column headings, or cross-tab breaks, that run horizontally across the top of a computer table.

Base
The number on which the percentages in a table are calculated.

Baseline market segmentation study
The first market segmentation study conducted by an organization.

Basic research
Research aimed at expanding knowledge rather than solving a specific, pragmatic problem.

Benchmark
A control source against which you compare the area you are studying. For example, you may compare the results of a study in one state to the results of the nation as a whole.

Bias
A systematic tendency of a sample to misrepresent the population. Biases may be caused by improper representation of the population in the sample, interviewing techniques, wording of questions, data entry, etc.

Bipolar scale
A scale with two negative, opposite end points and a midpoint representing the ideal situation. Examples: comfortable/uncomfortable, soft/hard, too spicy/too bland.

Briefing
A meeting in which a client and researcher discuss the client's information needs so that the most appropriate research methodology can be recommended.


C

Call record sheet
Interviewer log which lists the number and results of a contact.

Callback
An attempt to reach a person who could not be reached on the first try or a follow -up or after-use interview.

CAPI (computer-aided personal interviewing)
Interviewer-administered surveying, using a computer-based questionnaire.

CASI (computer-aided self-administered interviewing)
Self-administered surveying, using a computer-based questionnaire.

Cathode-ray tube (CRT)
A computer terminal with a keyboard and monitor. Used in research to display questions and enter responses directly into the computer-based questionnaire.

CATI (computer-aided telephone interviewing)
Interviewer-administered telephone surveying using a computer-based questionnaire.

Cell size
Smallest unit or segment quantity of an individual variant within a test program.

Census
A sample consisting of the entire population.

Central-location study
A survey conducted at a conveniently located site to which respondents come to be interviewed.

Chi-square
Chi-square tests are done to determine whether or not two nominal scaled variables are independent or correlated.

Clarifying
A follow-up technique for getting complete responses to open-ended questions by asking respondents to explain general terms in their answers. Also see probing.

Closed-end question
Questions that ask the respondent to choose from a limited number of pre-listed answers.

Coding
The process of translating responses to open-ended questions into numerical form for data processing.

Cognitive component of attitudes
An individual's knowledge and beliefs about an object.

Cognitive dissonance
Dissonance arises after a major purchase (e.g., a car) when alternatives are recommended and/or dislike emerges with the choice. To eliminate the discomfort of dissonance, the consumer will seek to rationalize the original choice, in other work, find positive advantages and ignore the negative.

Cohort
A group of individuals having a statistical factor (age, race, etc.) in common in a demographic study.

Cohort measures
Analysis of the activity of a cohort over an extended time period.

Column Binary
This data format allows multiple responses in a single column. Also known as IBM 360 column binary.

Comparative scales
A judgement comparing one object, concept or person against another on a scale.

Completion rate
The percent of qualified respondents completing an interview or study.

Concept description
A brief description of a new product or service.

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

Conclusions
The outcome or result; the section of the final report that contains the interpretation of the data in light of the research objectives. See also Executive Summary.

Conditional probability
The probability of a given event when additional information about the event is known. For example, the probability of rolling one on the toss of a die when we are given the additional information that the roll landed on an odd number.

Confidence intervals
The range around a survey result for which there is a high statistical probability that it contains the true population parameter.

Confidence level
The probability that a particular confidence interval will include the true population value.

Constant sum scales
Scales that ask the respondent to divide a given number of points, typically 100, among two or more attributes based on their importance to the individual.

Content analysis
A technique used to study written material (usually advertising copy) by breaking it into meaningful units.

Continuous variable
A quantitative variable that can assume an infinite number of values associated with the number on a line interval. Normally continuous variables are the result of some measurement process. Grade point average is a continuous variable because it can assume any value between 0.0 and 4.0.

Convenience sample
A sampling procedure that leaves the selection of respondents totally to the interviewers (or in the case of the Internet, the respondents), with no quotas or qualifications imposed. It consists of those units of the population that are easily accessible.

Co-op payment
The payment provided to participants as an incentive to answer surveys or come to a focus group. The amount varies dramatically, based on the difficulty of recruiting the participants. Also called the honorarium or incentive.

Correlation analysis
Analysis of the degree to which changes in one variable are associated with changes in another variable.

Cross-tabulation
Examination of the responses to one question relative to responses to one or more other questions.

Custom marketing research
Customized marketing research to address specific projects for corporate clients.

Customer satisfaction research
Research conducted to measure overall satisfaction with a product or service and satisfaction with specific elements of the product or service.

D

Data
The collection of observations.

Data processing
Organization of data for the purpose of producing desired information; involves recording, classifying, sorting, summarizing, calculating, disseminating and storing data.

Database management software
Computer programs in which data are captured on the computer, updated, maintained and organized for effective use and manipulation of data.

Demographics
Description of the vital statistics or objective and quantifiable characteristics of an audience or population. Demographic designators include age, gender, marital status, income, family size, educational level, occupation and other personal or household characteristics.

Dependent variable
A symbol or concept expected to be explained or caused by the independent variable. It is the variable measured on each subject to determine whether its value is affected by the independent variable. Also known as criterion  variable.

Depth interview
One-on-one interviews that probe and obtain detailed answers to questions, often using non-directive techniques to uncover hidden motivations.

Dichotomous questions
Questions that ask the respondent to choose between two answers.

Direct computer interviewing
Consumers are intercepted in a mall or other central location and interviewed by a computer that asks questions and accepts responses.

Disappointment score
The proportion of respondents in a product test who indicate, after trying the product, that they would not buy it.

Discrete variable
A quantitative variable that can assume a finite, or at most, a countable number of values such as the number of children in a family.

Discretionary income
The amount of money people have for spending after taxes and necessities are paid for. Also known as disposable income.

Disguised observation
The process of monitoring people, objects, or occurrences that do not know they are being watched.

Disk-by-mail (DBM)
Self-administered surveying using a computer-based questionnaire which is mailed to participants. (This can also be done over the Internet).

Disposable income
The income available to persons for spending or saving after taxes have been deducted. Also known as discretionary income.

E

Editing
The process of ascertaining that questionnaires were filled out properly, completely and accurately.

Efficiency
The degree to which the sample represents the population. See also precision.

Elasticity
Measures the extent volume shifts in response to a shift in the variable under consideration.

Electronic data processing (EDP) systems
Information systems that manipulate raw data with little intrinsic meaning to reflect transactional relationships, such as declarative and summary reports.

Error checking routines
Computer programs that accept instructions from the user to check for logical errors in the data.

Estimate
A numerical value obtained from a statistical sample and assigned to the population parameter.

Executive interviewing
The business equivalent of in-depth telephone interviewing or door-to-door interviewing.

Executive summary
The portion of a research report that explains why the research was done, what was found and what those findings mean, and what action, if any, management should undertake. See also conclusion.

F

Field management companies
Firms that provide support services, such as questionnaire formatting, screener writing, and data collection to full-service research companies.

Field service
Collection of survey data.

Final report
The document that the researcher develops at the conclusion of the research project. Its length varies, but a typical final report includes several sections: a summary of the methodology used, a review of the key findings, and the conclusion or interpretations or what the findings mean in light of the research objectives. Some final reports also contains a recommendation section consisting of suggestions for the client's next steps based on the conclusions of the research.

Findings
The portion of the final report wherein the facts from the research are summarized. The findings section does not interpret the information but reports the findings on which the interpretation will be based.

Fixed field
A way of laying out or formatting list information a computer file that puts every piece of data in a specific position relative to every other piece of data. If a piece of data is missing from an individual record, that space is not filled. Any piece of data exceeding its assigned space limitation much be abbreviated.

Focus group
A qualitative market research technique in which a group of participants (approximately 10) of common demographics, attitudes, or purchase patterns are led through a discussion of a particular topic by a trained moderator.

Forecast
An estimate, based on assumptions about future trends in births, deaths and migration, or of a demographic characteristic, such as population or number of households. Forecasts and projections are terms that are often used interchangeably.

Frequency
A measure of how often an event occurs; a count of the number of subjects falling in the different categories.

G

Geographics
Any method of subdividing a list based on geographic subdivisions.

Graphic rating scales
Graphic continuums anchored by two extremes presented to respondents for evaluation of a concept or object.

Grid Test
A means of testing more than one variable at a time.

Gross income
The total amount of money people have before taxes and necessities are paid for.

H

Head of household
A term no longer used by the U.S. Census Bureau (although often used in the research industry). The new term is householder. The householder is the person who completed the Census Questionnaire.

Hedonic scale
A scale for measuring general, overall opinion of a product.

Homogeneous groups
Groups in which the units or individuals have extremely similar characteristics.

I

Incentive
The payment to participants for answering a survey. The amount varies dramatically, based on the difficulty of recruiting the participants and the topic. Also called honorarium or co-op payment.

Incidence
Any figure referring to the percentage of people in a category. (Example: incidence of users, incidence of people qualifying for a study).

Income
As defined by the Census Bureau, income is a wage or salary income; self-employment income, interest, dividend, or net rental income; Social Security income; public assistance income; all other income, which includes unemployment compensation, veterans' payment, pensions, alimony, etc.

Independent variable
A variable that is controlled or manipulated by the researcher. See also predictor variable or factor.

Intelligent data entry
The logical checking of information being entered into a data entry device.

Intercept
A recruitment method in which an interviewer stops people in a mall or other public location and administers a survey.

Internal database
Database developed from data within the organization.

Interval
Taking a given number of units equally selected over the full population of the study. The nth number interval is derived by dividing the total number of units by the sample number desired. Also known as nth selection.

Interval scale
Ordinal scale with the additional property that the distance between observations is meaningful. An example would be the temperature. See ratio scale.

Interviewer
The person responsible for administering a questionnaire.

Interviewer error
Error that results from conscious or unconscious bias in the interviewer's interaction with the respondents.

Interviewer's instructions
Written directions to the interviewer on how to conduct the interview.

Itemized rating scales
Scales in which the respondent selects an answer from a limited number of ordered categories.

J

Judgement sample
A sample containing certain type of respondents, who are selected based on the judgement that their attitudes or behavior will be representative of the population.

K

Key verifying
Having two operators enter the same data to verify that entry is accurate.

Keypunch
Means of converting hard copy to machine-readable form by punching holes in either cards or paper tape (rarely used anymore but is still a term used to mean data entry).

L

Level of significance
Probability of making a Type I error.

Lifestyle research
Research that attempts to explain behavior by analyzing people's attitude, hobbies, activities and opinions. Often associated with psychographic research.

Likert scale
A scale in which the respondent specifies a level of agreement or disagreement with statements that express a favorable or unfavorable attitude toward the concept under study. See also semantic differential.

Longitudinal study
A long-term survey based on repeated analysis of either the same sample (called a panel study) or new samples chosen at regular intervals.

M

Machine cleaning
Cleaning data from selected columns based on user specific conditions (i.e., skip patterns).

Machine-readable data
Imprinted alphanumeric data that can be read and converted to magnetic form by an optical character reader.

Mail panels
A study in which participants are pre-contacted and screened, then periodically sent questionnaires.

Mall intercept interviewing
Shoppers are intercepted in public areas of malls and interviewed face-to-face.

Marginal
A computer-generated frequency count of the number of people giving each answer to all the questions in a questionnaire. Also called an 80-column dump. Often used to monitor entry of valid codes and correct use of skip patterns.

Market
Total of all individuals or organizations that represent potential buyers.

Market segmentation
The process of dividing a total market into sub-groups of consumers who exhibit differing sensitivities to one-or more marketing mix variables.

Marketing
The process of planning and executing the conception, pricing, promotion and distribution of ideas, goods, and services to create exchanges that satisfy individual and organizational objectives.

Market concept
The business philosophy that a company's effort should be adapted to the needs and wants of its customers.

Marketing mix
The unique blend of product pricing, promotion, offerings, and distribution designed to meet the needs of a specific group of customers.

Marketing research
The planning, collection, and analysis of data relevant to marketing decision making, and the communication of the results of this analysis to management.

Mean
The sum of the values for all observations of a variable divided by the number of observations. Also called average.

Measurement
Process of assigning numbers or labels to things in accordance with specific rules to represent quantities or qualities of attributes.

Median (Mid-point)
The numerical observation that divides the distribution of observations in half. Sometimes referred to as the second quartile.

Methodology
The research procedures used; the section of the final report in which the researcher outlines the approach used in the research, including the method of recruiting participants, the types of questions used, and so on.

Metric scale
Identifies categories of the variable in which observations can be ranked from smallest to largest and the distance between variables is meaningful and the ratios of the observations are meaningful. Also known as ratio scale. Examples include weight, height, age, etc.

Mode
The most frequently occurring measurement. The peak of a frequency curve.

Multiple choice questions
Questions that ask a respondent to choose from a list of more than two answers.

Multivariate analysis
Any statistical procedure that simultaneously analyzes several measurements (variables).

Mutually exclusive
Events are said to be mutually exclusive if they have no intersection.

Mystery shoppers
People employed to pose as consumers and shop at the competitors and their own stores to compare prices, displays, etc.

N

Nominal scale
Identifies categories of the variable. Categories are called classes or levels. Example: male/female, user/non-user.

Non-response bias
Error that results form a systematic difference between those who do and do not respond to the measurement instrument.

Non-sampling error
All the sources of bias or inaccuracy in a study besides sampling error. Examples: leading by the interviewer, recording/data entry errors.

Normal distribution
A continuous distribution that is bell shaped and symmetrical about the mean.

Nth selection
Statistical means of taking a given number of names or units equally selected over the full population of study. The nth number interval is derived by dividing the total number of units by the sample number desired. Also known as interval.

Null hypothesis
The statement being tested in a test of significance.

Numeric database
Database containing original survey data on a wide variety of topics.

O

Objectives
The information to be developed from a study to serve the project's purpose.

Observation
The value that the variable assumes for a single unit of the sample.

Observation research
Descriptive research that monitors respondents' actions without direct interaction. Sometimes called a quasi-experiment.

One-by-one
Unlabeled table with one column serving as the banner (column headings) and another column serving as the stub (row headings), for all of the respondents in a study or for a sub-sample of those respondents.

One-group pretest-post test design
Pre-experimental design with pre and post measurements but no control group.

One-on-one
A qualitative research technique in which a moderator interviews one participant.

One-way frequency table
A table showing the number of responses to each answer of a survey question.

Open-ended question
A question that has no pre-listed answers which requires the respondent to answer is his or her own words. Also known as a subjective question.

Order bias
Bias created by the order in which products or questions are placed. Rotations are used to eliminate this bias.

Ordinal scale
Identifies categories of the variable that can be ranked from smallest to the largest, but the distance between observations is not meaningful. An example would be a question that attempts to record the degree of opinions using terms such as poor, fair, good and excellent.

Outlier
Value data that is relatively far from a certain point or center. This will cause the mean (average) to be very different from the median (mid-point).

Over-recruit
The extra people who are recruited for a pre-post study or pre-recruit to compensate for the inevitable no-shows.

P

Packaging tests
Tests used to gauge reactions to different packaging approaches.

Paired comparison
A test in which a respondent evaluates two products in a set based on some stated criteria.

Panel
A survey in which the same respondents are interviewed several times over an extended period. Also called longitudinal analysis. Group interviews (focus groups) are sometimes called panels.

PAPI (paper and pencil interviewing)
Survey in which the respondent fills out a traditional paper questionnaire, usually administered by interviewer. See also SAQ.

Parameter
Numerical summary measure of a population distribution.

Participant
A person included in a focus group, survey or study. Also called respondent, unit, subject, experimental unit or unit of analysis.

Penetration analysis
Study of the market share held by a given firm or product within various universes by classification or other demographic characteristics.

Per capita income
The average amount of income per person in a population, regardless of age or labor force status. It is derived by dividing the total income by the total population.

Percentile
A value on the scale of 100 that indicates the percent of a distribution that is equal to or below it.

Personal income
Money income plus certain non-cash benefits.

Photo sort
The respondent sorts photos of different types of people, identifying those photos that respondent feels would use the specific product or service.

Physical control
Holding the value or level of extraneous variables constant throughout the course of an experiment.

Placement interview
An interview in which a respondent is recruited and given the product to use in a product test.

Population
The collection of all objects that are of interest to the statistician. The elements of a population may be called units or subjects. Also known as the universe.

Population distribution
A frequency distribution of all the elements of a population.

Positioning
Location of a brand or product in consumers' minds relative to competitive products.

Predictive dialing
A computer automatically dials telephone numbers and passes connected calls to available interviewers.

Pre-recruited central-location test
A survey conducted at a conveniently located site to which respondents - who have been previously contacted and qualified - come to be interviewed.

Presentation software
Personal computer software that provides easy-to-use platforms for creating effective reports and presentations.

Pre-test
A trial run of a questionnaire sent to a small sample to be sure that actual responses are clear and that any problems with the questionnaire are detected.

Primary data
New data gathered to help solve the problem at hand. As compared to secondary data with is previously gathered data.

Primary research
Conducting research to collect new data to solve a marketing information need. See also secondary research.

Probability sample
A sample in which every unit has an equal (non-zero) and known probability of being selected. Sometimes called random sample.

Probing
A follow-up technique for getting complete responses to open-ended questions by asking. Also see clarifying.

Processing error
Error that results from incorrect transfer of information from the data collection document to the computer.

Product concept testing
The testing of new product ideas before they have been turned into prototypes.

Product placement study
A type of test in which respondents try a product under normal usage conditions. Example: in-home test of a food product. Also called a product test.

Product positioning research
Research used to determine how competitive brands are perceived relative to each other on key dimensions.

Product pricing research
Research used to measure consumer sensitivity to different prices for a product.

Product prototype tests
Tests conducted to obtain the reactions of targeted customers to early working versions of new products.

Professional respondent
A participant who attends many sessions by volunteering for the recruitment lists of different facilities. Most moderators seek to eliminate professional respondents from groups, since they do not generally respond in the same objective way that fresh respondents.

Projectability
The capability of research results to be extrapolated to the larger universe, on the assumption that the sample is representative of the total.

Psychographics
Research that attempts to explain behavior by analyzing people's personality traits and values. Often associated with lifestyle research.

Purchase intent scales
Scales used to measure a respondent's intention to buy a product.

Purpose
The reason a research project is being conducted; usually focuses on the decisions for which information from the study will be used.

Q

Qualitative
Research data not subject to quantification or quantitative analysis; characterized by the absence of empirical measurements and an interest in subjective evaluation. Qualitative methodologies includes focus groups, mini-groups, one-on-ones and open ended-questions.

Qualitative variable
A variable whose values are classifications or categories and are not subject to quantitative interpretation.  Examples include sex, occupation, marital status, etc.

Quantitative research
Research conducted for the purpose of obtaining empirical evaluations of attitudes, behavior or performance.  Designed to generate projectable numerical data about a topic.

Quantitative variable
A variable whose values are numerical in nature.  Examples include weight, age, income, etc.  Quantitative variables are further classified as being either discrete or continuous.

Quartiles
The division of the observation distribution into quarters (in the same way the median divides the distribution in half).

Quasi-experiments
Studies in which the researcher lacks complete control over the scheduling of treatment or must assign respondents to treatment in a non-random manner.

Questionnaire
A set of questions designed to generate data necessary for accomplishing the objectives of the research project.

Quota sample
A sampling procedure that includes specified numbers of respondents having characteristics known or believed to affect the subject being researched.  Selection is by non-probability means.  A moderator might set a quota of having half the group be users of Brand X, or one-fourth be aware of Product Y.

R

Race
As defined by the U.S. Census Bureau:  Aleut, American Indian, Asian, Black, Chinese, Eskimo, Filipino, Guamanian, Hawaiian, Japanese, Korean, Samoan, Vietnamese, White, or "other".

Random
Being or relating to a set or element in which each set or element has an equal (non-zero) probability of occurring.

Random error
Error that affects measurement in a transient, inconsistent manner.

Random sampling
A sample in which each unit has an equal and independent chance of selection.  Also known as probability sample.

Random variable
A variable whose value is determined by the outcome of an experiment in which the outcome is subject to chance.  For example "heads" or "tails" is a random variable for a coin toss.

Random-digit dialing
A telephone sampling procedure that generates random combinations of telephone numbers in order to include unlisted numbers in a survey sample.

Randomization
The random assignment of subjects or treatment conditions to ensure equal representation of subject characteristics in all groups.

Range
The highest value for a variable minus the lowest value for that variable.

Rank-order scales
Scales in which the respondent compares one item with another or a group of items against each other and ranks them.

Rank-order stubs
This refers to controlling the arrangement of stubs in a particular table according to the frequency of mentions for each stub.

Rate
A fixed ratio between two things.

Ratio
A measure that expresses the relative size of two numbers

Ratio scale
Identifies categories of the variable in which observations can be ranked from smallest to largest and the distance between variables is meaningful and the ratios of the observations are meaningful.  The ratio scale is for variables that have a uniquely defined zero.  Examples include weight, height, age, etc.

Recode
To create a new variable that represents a specific condition based on existing data.

Recommendations
The section of the final report that suggests the next action steps a client could take, based on the conclusions of the research.

Recruitment
The process of securing participants for focus groups or panel.

Related samples
Samples in which the measurement of a variable in one population may influence the measurement of the variable in the other.

Reliability
Measures that are consistent from one administration to the next.

Repeat rate
The proportion of first-time users of a product who purchase the product at least a second time.

Repeat-pairs technique
A product testing procedure in which respondents express a preference between two products, then repeat the task with an identical pair of products.

Replicate
Geographically representative sub-sample which is systematically selected from the entire sample.

Representative sample
A sample in which each unit has an equal and independent chance of selection.  Also known as probability sample or random sampling.

Re-screening
A brief interview conducted with potential participants when they arrive at a facility to ensure that they really qualify for the session.  Re-screening normally uses some of the questions that were originally asked when the participants were originally recruited.

Research design
The plan to be followed to answer the research objectives; the structure or framework to solve a specific problem.

Respondent
The individual from which data are collected.  Also called participant, unit, unit of analysis, subject or experimental unit.

Response bias
Error that results from the tendency of people to answer a question falsely, through deliberate misrepresentation or unconscious falsification.

Rotation
Changing the order of products or questions in order to eliminate order bias.

Rule
A guide or a command that tells a researcher what to do.

S

Sample
A subset of the population of interest selected for a research study.  It is a finite portion that is used to study the characteristics of concern in the population.

Sample distribution
A frequency distribution of all the elements of an individual sample.

Sample population
The population from which the sample is obtained.

Sampling
The method of selecting a specified portion, called a sample, from a population, from which information concerning the whole can be inferred.

Sampling distribution of the proportion
A frequency distribution of the proportions of many samples drawn from a particular population.  It is normally distributed.

Sampling distribution of the sample means
A frequency distribution of the means of many samples drawn from a particular population.  It is normally distributed.

Sampling distribution of the sample statistic
The probability distribution associated with the various values that the statistic could assume in repeated sampling.

Sampling error
The estimated inaccuracy of the results of a study when a population sample is used to explain behavior of the total population.

Sampling fraction
The proportion of the number of sample elements to the number of population elements.

Sampling frame
A listing of all elements in the sampled population.

Sampling interval
Taking a given number of units equally selected over the full population of study.  The nth number interval is derived by dividing the total number of units by the sample number desired.  Also known as nth selection or interval.

Sampling unit
The elements available for selection at during the sampling process.

SAQ (self-administered questionnaire)
A questionnaire completed with no interviewer involvement, such as a mail survey.

Scale
A closed-ended question for measuring attitudes.  A set of symbols or numbers so constructed that the symbols or numbers can be assigned by a rule to the individual (or their behavior or attitudes) to whom the scale is applied.

Scaled-response questions
Multiple choice questions in which the choices are designed to capture the intensity of the respondent's answer.

Screener
Questions used to screen for appropriate respondents.

Secondary data
Data that has been previously gathered.

Secondary research
Analyzing information from previously conducted research projects.  See also primary research.

Sectional center facility (SCF)
Geographic areas represented by the first three digits of a ZIP code.

Segment
Portion selected based on a special set of characteristics.

Selection
Process of choosing records using specific criteria from a population.

Selection bias
Systematic differences between the test group and control group because of a biased selection process.

Selection error
Error that results from following incomplete or improper sampling procedures.

Selective perception
The ability of a listener or reader to filter out some information for conscious or subconscious reasons.

Selective research
Research to choose among several viable alternatives identified by programmatic research.

Semantic differential
A method of examining the strength and weaknesses of a product or company versus the competition by having respondents rank it between dichotomous pairs of words or phrases that could be used to describe it; the means of the responses is then plotted in a profile or image.  Se also Likert scale.

Sentence and story completion
Tests in which the respondent completes sentences or stories in their own words.  The purpose of this technique is to enable participants to delve into certain areas that they may otherwise find difficult to discuss.

Sequential testing
A testing procedure in which a respondent tries one product, evaluates it, then tries and evaluates a second product.

Sex ratio
The number of males per 100 females in a population.

Shopper patterns
Drawings that record footsteps of a shopper through a store.

Short census form
U.S. Census Bureau questionnaire that all Americans answer every 10 years.

SIC (standard industrial classification)
Classification (in a four-digit code) of business as defined by the U.S. Department of Commerce.  Pseudo SICs are SIC modifications which add a fifth or sixth character to allow for greater specificity.

Significant difference
In mathematical terms, difference between tests of two or more variables.  The significance difference varies with the confidence level desired.

Significance testing
Tests for determining whether observed differences in a sample are sufficiently large as to be caused by something other than mere chance.

Sign-out sheets
A control document used by a facility to keep track of co-op payments to participants.

Simple random sample (SRS)
A sample selected in such a way that every element of the population has a known and equal chance of being chosen for the sample.  Also called random sample.

Simulated sales test
A procedure designed to estimate a product's sales potential by simulating trial and use conditions of the marketplace.

Site evaluation
Determining, through an analysis of a given area's demographic and economic characteristics, whether it offers a good market for a product or service.

Skip pattern
Requirement to pass over questions in response to respondent's answer to a previous question.

Specialized service or support firms
Companies that handle a specific facet of research, such as data processing or statistical analysis, for many corporate clients.

Specifications
The criteria for participants in a focus group, involving their demographic characteristics, product usage, product awareness, and so on.

Spread data
To spread out data contained in multiple-punched columns in order to convert data to ASCII format and not loose the data.

Stability
Lack of change in results from test to retest.

Standard error
The standard deviation of a distribution of sample means; the square root of the variance of the sampling distribution.

Stapel scale
A scale, ranging from +5 to -5, that requires the respondent to rate how close and in what direction a descriptor adjective fits a given concept.

Starting point
The first number selected of an Nth sampling interval.

Statistical control
Adjusting for the effects of confounded variables by statistically adjusting the value of the dependent variable for each treatment condition.

Statistical inference
Drawing conclusions about populations based on a sample.

Statistics
The science of collecting organizing or describing data, and ultimately drawing conclusions from it.

Stub
The responses to the question being tabulated, which run vertically down the left side of a computer table.

Subjective question
A question that has no pre-listed answers which requires the respondent to answer in his or her own words.  Also known as open-ended question.

Supervisor's instructions
Written directions to the field service on how to conduct a survey.

Survey objectives
The decision-making information sought through the questionnaire.

Survey research
Research in which an interviewer interacts with respondents to obtain facts, opinions and attitudes.

Syndicated research
Studies in which the sponsoring research company defines the audience to be surveyed and the interval between studies and the questions to be asked.  Clients share the same results and cost.

Systemic error
Error that results from the research design or execution.

T

Table of random digits
A table consisting of digits in a completely random order.

Target population
The population which is being studied.

Telephone sample
A group of individuals who are surveyed by telephone.

Test market
Trial market for a new product or service offer.

Test-retest reliability
The ability of the same instrument to produce consistent results when used a second time under conditions as nearly the same as possible.

Time use survey
A survey of how people use their time, taken by asking people to record what they do and how they do it in a diary over several days or weeks.

Topline
Preliminary results from a project, usually showing responses of the total sample to a few key questions.

Tracking
Studies repeated over time to monitor changes in a brand or product category.

Trial rate
Measures the proportion of people who buy a product at least once.

Trimmed mean
Obtained by trimming a percent of the high and low ends of a distribution and finding the mean of the remaining distribution

T-test
T-tests are used to see whether or not the means from two banner points are statistically different.

Type I error
Rejection of a null hypothesis when it is true.

Type II error
Failing to reject null hypothesis that is false.

U

Unbiased samples
Samples obtained from sample designs in which there is no bias and all sampling error comes from random sources.

Unidemensional scaling
Procedures designed to measure only one attribute of a respondent or object.

Unipolar
An ordinal scale with one positive end and one negative end.

Universe
The set of all the units from which a sample is drawn. Also called population.

Unstructured observation
A study in which the observer simply makes notes on the behavior being observed.

Unstructured segmentation
Process of segmenting a market using data and analysis when no prior ideas are held about the number of segments, what they are, or how and why they are different.

V

Validation
The process of ascertaining and re-contacting respondents to confirm that interviews were conducted correctly.

Value data
Data that requires more than one column to read the entire answer. It contains a group of consecutive columns where the data is treated as one value. For example,  # of months, # of employees (without giving ranges), etc.)

Variability
Differences in the measurement of variables.

Variable
Any characteristic that can be measured on each unit of the population.

Variance
The measure of the variability of the variable. The statistical measure of how similar a population is in a characteristic being studied. It is the average squared distance of all measurements from the mean.

Verbatim
A transcript of the actual comments participants make to an open-ended question. These comments can then be coded into numerical form for data processing.

W

Watts Marketing Research Services (WMRS)
The best, most thorough, marketing research processing firm in the world!

Weighting
Assigning a numerical coefficient to an item to express its relative importance in a frequency distribution.

Word association tests
Tests in which the interviewer says a word and the respondent must mention the first thing that comes to mind.

Z

Zip code demographics
The demographic characteristics of a population living in a particular ZIP code.

Z-test
A statistical test for two independent proportions. It addresses the question of whether the proportions of a particular response (a single stud) are equal for two independent banner points.