Glossary

Case Study a comprehensive description and analysis of a single situation. Causal Relationship a precondition influencing a variable of interest, or, more strictly, a change in one variable that produces a change in another variable. Causal Research research having very specific hypotheses that is usually designed to provide the ultimate level of understanding — a knowledge that one construct under certain conditions causes another construct to occur or to change. Census Data the demographic, economic, and social statistics of a population. Census Tract a group of city blocks having a total population of more than 4000 and generally used to approximate neighborhoods. Centroid the average value of the objects contained in the cluster on each of the variable making up each object's profile. Chi-Square Statistic a measure of association between two nominally scaled variables. City Block the smallest identifiable unit in the U.S. Census, being bounded by four streets or some other physical boundary. Classification Matrix matrix containing numbers that reveal the predictive ability of the discriminant function. Classification Variable used to classify respondents, such as demographic and socioeconomic measures. Clinical Focus Groups focus groups where the moderator probes the subconscious of consumers. The moderator has to be proficient in sociology and psychology. Closed-Response (or Structured) Question a question accompanied by the presentation of responses to be considered by the respondent. Cluster Analysis a set of techniques for grouping objects or persons in terms of similarity. Cluster Sampling a sampling method where a random sample of subgroups is selected and all members of the subgroups become part of the sample. Clutter/Awareness the percentage who recalled a brand was advertised when exposed in a "Clutter" of seven ads in a McCollum/Speilman test. Coding the categorization and numbering of responses. Cognitive/Knowledge Component that part of attitude representing the information a person knows about an object, person, or event. Communality the proportion of a variable's variance explained by all of the factors in a factor analysis solution. Comparative Scale a type of scale with some form of explicit or implicit comparison built into the scale. Compensatory Model any multiattribute model in which one attribute compensates for another in the overall preference for an object. Complementary Pricing the pricing strategy used by firms to price complementary products. They usually price the main product at a low price while the complement is charged at a higher price. Complete Linkage linkage procedure similar to single .................. age except that the clustering criterion is based on the longest distance. Completely Randomized Design the simplest type of .............tical design in which the experimental treatment ........ signed to test units on a random basis. Completion Test a projective technique in which the respondent is asked to completed a series of sentences. Compositional Approach an attitude measurement approach in which the overall preference judgment for ................... object is obtained by summing the evaluative rating .................. attribute multiplied by the importance of the attribute. Computer-Assisted Telephone Interviewing (CATI) ........... phone interviews conducted with the aid of computers that reducing interviewer error. Computer Interactive Interviewing (CII) the respondent interacts directly with the computer. Computer-Retrievable Databases secondary records accessible by a computer system. Concept Test a test of a product concept where the concept is evaluated by a sample of the target segment. Concurrent Validity criterion validity that is established a correlating the measurement score with the criterion ............... able, both measured at the same time. Conjoint Analysis a method of obtaining the relative work or value of each level of several attributes from rank order preferences of attribute combinations. Consensus/Face Validity is invoked when the argument is made that the measurement so self-evidently reflects or represents the various aspects of the phenomenon that there can be little quarrel with it. Consideration/Evoked Set all the alternative that potential buyers would consider in their next purchase of the product or service. Constant-Sum Scale a scale in which the respondent must allocate a fixed number of points among several object as reflect the relative preference for each object. Construct a concept, usually psychological such as attitudes and values, that is not directly observable. Construct Equivalence deals with how the researcher and the subjects of the research see, understand, and code a particular phenomenon. Construct Validity the ability of a measurement instrument to measure a concept or "construct"; construct validity as generally demonstrated by showing both convergent and discriminant validity. Consumer-Direct a full service distribution channel that has its genesis in today's PeaPod and NetGrocer. Content Analysis a technique used to study written material by breaking it into meaningful units, using carefully applied rules. Contrived Observation a behavioral project test that assumes that the response of people placed in a contrived observation situation will reveal some aspects of their underlying beliefs, attitudes, and motives. Contingency Coefficient a chi-square statistic corrected for sample size. Continuous Panel Studies collect a series of measurements on the same sample of test units, over an extended period of time. Continuous Purchase Panel a fixed sample of respondents who are measured on several occasions over a period of time. Continuous-Rating Scales respondents rate the objects by placing a mark at the appropriate position on a line that runs from one extreme of the criterion variable to the other. Contrived Observation an observation method in which people are placed in a contrived situation so that their responses will reveal some aspects of their underlying beliefs, attitudes, and motives; examples are tests of variation in shelf-space, product flavors, and display locations. Control Group the group of subjects not exposed to the experimental treatment. Controlled Distribution Scanner Markets (CDSM) distribution for new product test is prearranged and results are monitored with scanner data. Convenience Sampling a sampling method in which convenient sampling units are contacted, such as church activity groups or student classes. Convergent Validity the ability of a measurement instrument to correlate or "converge" with other supposed measures of the same variable or construct; the opposite of discriminant validity. Copy Test Validity the ability to predict advertising response. Correlation a number between +1 and -1 that reflects the degree to which two variables have a linear relationship. Correspondence Analysis a technique for producing perceptual maps using binary data. Cost-Benefit Analysis an analysis to determine the value of information sought from marketing research, by evaluating the cost required to collect the information and the benefit in dollar value provided by the information. Criterion/Empirical Validity the validity of a measurement instrument as determined by empirical evidence that correlates the measurement instrument with other "criterion" variables. Critical Path Method (CPM) a network approach that involves dividing the marketing research project into multiple components and estimating the time required to complete each component/activity. Cross-Tabulation/Contingency Table Analysis the determination of a frequency distribution of subgroups. Cross Validation/U-Method makes use of all the available data without serious bias in estimating error rates. Cyclical Indexes a representation of the effects of business cycle fluctuations in making a forecast. Data unassimilated facts about the market. Data Analysis Error errors that arise due to the faulty procedures employed in coding, editing, analyzing, and interpreting data. Data Editing identifies omissions, ambiguities, and errors in responses. Database an organized store of data, usually within a computer. Day-After-Recall (DAR) the percentage of the audience who can recall something specific about the commercial the next day. Decision Support System (DSS) a collection of rules, procedures, and models for retrieving data from a database, transforming it into usable information, and disseminating it to users so that they can make decisions. Decompositional Approach attitude measurement approach in which the utilities of each attribute are obtained from the overall preference judgment for each object. Degree of Freedom (DF) the number of bits of "free" or unconstrained data used in calculating a sample statistic or test statistic. Delphi Approach a group judgment method where each member makes an individual judgment and then each member is given an opportunity to revise his or her judgment after seeing the others' initial judgments, until, after several iterations, the group members each their conclusion. Demographic Shift changes in physical and socioeconomic characteristics of a population such as age, ethnicity, income, and so on. Dependence Techniques appropriate when one or more variables can be identified as dependent variables and the remaining as independent variables. Descriptive Research research that usually is designed to provide a summary of some aspects of the environment when the hypotheses are tentative and speculative in nature. DETAILER a decision calculus model for determining the sales force allocation by market and by product line. Diary Panel the basic data-gathering instrument for local TV and radio ratings. Direct Observation an observation method in which the researcher directly observes the person or behavior in question. Discriminant Analysis a statistical technique for developing a set of independent variables to classify people or objects into one or more groups. Discriminant Function the linear combination of variables developed by discriminant analysis for the purpose of classifying people or objects into one or more groups. Discriminant Validity the ability of a measurement instrument not to correlate with supposed measures of other variables or constructs; the opposite of convergent validity. Disproportionate Sampling best used when one of the groups or subgroups of the population is a relatively small percentage of the population., Dollarmetric Scale survey that provides a direct measure of the brand name's value. Door-to-Door Interviewing interviewing in which consumers are interviewed in person in their homes. Drop-Off Approach the hand delivery of a questionnaire to sampling points. Dummy/Binary/Dichotomous/Instrumental/Qualitative Variable a variable taking on the values of either 0 or 1, which is used to denote characteristics that are not quantifiable. Efficiency a criterion used to judge whether a market research study produces that maximum amount and quality of information for the minimum expenditure of time and money. Eigenvalue represents the amount of variance in original variables that is associated with factor. Empathic Interviewing an exploratory way of research that draws from the wisdom of sociology, psychology, market research, and anthropology to help researchers probe beneath generalizations and identify the social factors that influence consumer behavior. Evaluative Research is carried out to evaluate performance of programs, including tracking advertising recall, corporate and brand image studies, and measuring customer satisfaction with the quality of product and service. Expected Value the value obtained by multiplying each consequence by the probability of that consequence occurring and summing the products. Experiment study in which conditions are controlled so that one or more independent variable(s) can be manipulated to test a hypothesis about a dependent variable. Experimental Control the control of extraneous variables through experimental procedures such as randomization or block designs. Experimental Control the control of extraneous variables through experimental procedures such as randomization or block designs. Experimental Error error that arises due to the improper design of the experiment. Experiment Group the group of subjects exposed to the experimental treatment. Experimental Treatments alternative manipulations of the independent variable being investigated. Experiments studies that require the intervention by the observer beyond that required for measurement. Exploratory Focus Groups focus groups commonly used at the exploratory phase of the market research process to aid in precise problem definition. Exploratory Research research that usually is designed to generate ideas when the hypotheses are vague or ill-defined. Exponential Smoothing in time-series extrapolations, the weighting of historical data so that the more recent data are weighted more heavily than are less recent data, by exponentially decreasing sets' of weights. External Source a marketing data source found outside of the organization. External Validity the applicability of experimental results to situations external to the actual experimental context. Extraneous Variable variables other than the manipulated variable the affect the response of the test units and hence the results of the experiment. Also known as the confounding variables. E-Commerce buying something electronically without talking to people or using invoices or any other paper to complete the business transaction. F Statistic the statistic used in the analysis of variance to test for differences in groups. Face/Consensus Validity the validity of a measurement instrument as determined entirely by subjective argument or judgment. Factor an underlying construct defined by a linear combination of variables. Factor Analysis a set of techniques for the study of interrelationships among variables, usually for the purposes of data reduction and the discovery of underlying construct ................ latent dimensions. Factor Loading the correlation (or sometimes the ............... weight) of a variable with a factor. Factor Rotation the generation of several factor analysis sections (factor loadings and scores) from the same data set. Factor Scores a respondent's score or value on a factor. Factorial Design an experimental design in which two or more experimental variables are considered simultaneously by applying each combination of the experimental treatment levels to randomly selected groups. Field Experiments experiments in which the experiment treatment is introduced in a completely natural setting. Field Services these suppliers concentrate on collecting data for research projects. Focus Group a group discussion focused on a series of topics introduced by a discussion leader; the group members are encouraged to express their own views on each topic and to elaborate on or react to the views of each other. Forced Exposure respondents are exposed to an ad in a facility as opposed to an "on-air" test in the home. Foreign Market Opportunity Analysis acquisition of information that would help the management to narrow the possibilities for international marketing activities. The aim of ........................ an exercise is to gather information to aid in managerial decision making. Frequency Distribution a report of the number of responses that a question has received. Full-Profile Approach a method of collecting data for tradeoff analysis in which respondents are given cards that describe complete product or service configurations. GANNT Charts a form of activity flowcharts that provide a schematic representation incorporating the activity, time, and personnel requirements for a given research project. Genotypic Sources of Refusal these pertain to why survey respondents refuse to participate on account of their inherent characteristics such as age, sex, occupation, and so on. Goodman and Kruskall's Tau a measure of association for nominally scaled variables based on a proportional reduction in error. Graphical Evaluation and Review Technique (GERT) essentially a second-generation PERT approach to scheduling, in which both the completion probabilities and activity costs to be built into a network representation are considered. Hierarchical Clustering a method of cluster analysis that starts with each object in its own (single-object) cluster and systematically combines clusters until all objects are in one cluster. History Effect any influence on subjects, external to an experiment, that may affect the results of the experiment. Hit Ratio percentage of cases classified correctly. Hold-Out Sample a sample used to test a model developed from another sample. Home Audit a method of collecting continuous purchase panel data in which the panel members agree to permit an auditor to check their household stocks of certain product categories at regular intervals. Humanistic Inquiry a method in which the researcher is immersed in the group or system under study. Hypothesis is a possible answer to the research question. Ideal Object the object the respondent would prefer over all others, including objects that can be conceptualized but do not actually exist; it is a combination of all the respondent's preferred attribute levels. Independence in statistics, the property that the knowledge of one variable or event offers no information as to the identity of another variable or event. Individual Depth Interview a qualitative research method designed to explore the hidden (deep) feelings, values, and motives of the respondent through a face-to-face interview with the researcher. Industrial Market a market for goods an services composed of industrial firms, other businesses, government agencies, and organizations in general, rather than individual consumers. Information data that have been transformed into answers for specific questions of the decision makers. Information System a system containing marketing data and marketing intelligence. Instrumentation Effect the effect of changes in the measuring instrument on the experimental results. Integrated Marketing communications a concept of marketing communications planning that recognizes the added value of a comprehensive plan that evaluates the strategic roles of a variety of communication disciplines and combines these disciplines to provide clarity, consistency, and maximum communication impact through the seamless integration of discrete messages. Intention/Action Component the part of an attitude that represents the person's expectations of future behavior toward the object, person, or event. Interactive Effect the case where the effect of one variable on another variable depends on the level of a third variable. Interdependence Techniques the variables are not classified as dependent or independent; rather, the whole set of interdependent relationships is examined. Interference Error error that occurs due to the failure of the interviewer to adhere to the exact procedure while collecting the data. Internal Records a marketing data source found within the organization. Internal Validity the ability of an experiment to show relationships unambiguously. Internet a global network connecting millions of computers. Interval Estimation the estimation of the interval in which an unknown population characteristic is judged to lie, for a given level of confidence. Interval Data data representing the responses obtained from interval and ratio scales. Interval Scale a scale with the property that units have the same width throughout the scale (i.e., thermometer). Intervening Variable any variable positioned between two other variables in a causal path. Interviewer Error a source of error in personal interviews due to the impression the respondent has of the interviewer and the way the interviewer asks questions, follows up partial answers, and records the responses. Intranets internal company networks. Itemized Category Scale a scale in which the respondent chooses among one of several response options or categories. Judgmental Sampling a nonprobability sampling method in which an "expert" uses judgment to identify representative samples. Jury of Executive Opinion an efficient and timely qualitative research approach that combines the judgments of a group of managers about forecasts, most commonly used in consumer products and service companies. Laboratory Experiment an experiment in which the experimental treatment is introduced in an artificial or laboratory setting. Laboratory Test Market a procedure whereby shoppers are exposed to an ad for a new product and then taken on a simulated shopping trip in a laboratory facility. Latin Square Design an experimental design that reduces the number of groups involved when interactions between the treatment levels and the control variables can be considered relatively unimportant. Lead User Analysis an approach where instead of just asking users what they have done, their solutions are collected more formally. Leading Indicators a variable that tends to predict the future direction of an object to be forecast. Likert/Summated Scale a scale developed by the Likert method in which the subject must indicate his or her degree of agreement or disagreement with a variety of statements related to the attitude object and which then are summed over all statements to provide a total score. Lockbox Approach the delivery by mail of a small, locked metal box containing a questionnaire and other interviewing exhibits. Magnitude Scaling a technique for measuring opinions using a ration scale instead of an interval scale. Mail Diary Method a method of collecting continuous purchase panel data in which panel members record the details of each purchase in certain categories and return a completed mail diary at regular intervals. Mail Panel a representative national sample of people who have agreed to participate in a limited number of mail surveys each year. Mail Survey the mailing of questionnaires and their return by mail by the designated respondents. Mall Intercept Surveys surveys conducted in malls by intercepting consumers who visit the mall. Market Potential the sales for the product or service that would result if the market were fully developed. Market Segmentation the development and pursuit of marketing programs directed at subgroups or segments of the population that the organization could possibly serve. Marketing Decision Support System combines marketing data from diverse sources into a single database that line managers can enter interactively. Marketing Planning and Information System a system of strategic and tactical plans and marketing data and intelligence that provides overall direction and coordination to the organization. Marketing Program Development the stage of the market planning process that deals with segmentation decisions, product decisions, distribution decisions, advertising and promotion decisions, personal selling decisions, and pricing decisions. Marketing Research the specification, gathering, analyzing, and interpretation of information that links the organization with its market environment. Marketing Research Methodologist an individual who has a balanced and in-depth knowledge of the fields of statistics, psychometrics, marketing, and buyer behavior and applies that knowledge to describe and infer causal relationships from marketing data. Manipulation the creation of different levels of the independent variable is known as manipulating the variable. Matching a procedure for the assignment of subjects to groups that ensures each group of respondents is matched on the basis of the pertinent characteristics. Maturation during a research study, changes within respondents that are a consequence of time. Mean the number obtained by summing all elements in a set and dividing by the number of elements. Measurement the assignment of numbers by rules to objects in order to reflect quantities of properties. Measurement Equivalence deals with the methods and procedures used by the researcher to collect and categorize essential data and information. Measurement Error error that occurs due to the variation between the information sought by the researcher and the information generated by a particular procedure employed by the researcher. Metropolitan Statistical Areas urban areas that constitute counties containing a central city with populations of at least 50,000. Monopolar Scale a scale bounded at each end by polar adjectives or phrases, one of which is the negation of the other. Mortality Effect the effect on the experimental results of respondents dropping out of an experiment. Moving Average using the moving average of the last n data points (e.g., the monthly averages for a year) to forecast. Multiattribute Model any model linking attribute judgments with overall liking or affect. Multidimensional Scaling (MDS) a set of techniques for developing perceptual maps. Multiple-Item Scales scales used in social research to measure abstract construct. Multiple Linear Regression linear regression where more than one independent variable is used. Multistage Designs a sampling procedure that consists of several sampling methods used sequentially. Multivariate Analysis the simultaneous study of two or more measures on a sample of objects. Need a want, an urge, a wish, or any motivational force directing behavior toward a goad. Need Research/Identification a type of concept generation research with the emphasis placed on the identification of unfulfilled needs that exist in the market. New-Product Research Process a sequential four size process consisting of concept generation, concept ................. and development, product evaluation and development ............ product testing. Nielsen Retail Index a retail store audit conducted by ........... Nielsen for four major groups of stores: grocery ............. drugs, mass merchandisers, and alcoholic beverages. Nominal Scale a measurement that assigns only ........................ cation or label to an object or set of objects. Nondirective Interview a type of individual depth interview in which the respondent is given maximum freedom ............. spond, within the bounds of topics of interest to the ......... viewer. Nonhierarchical Clustering Program permits objects ......... leave one cluster and join another as clusters are being formed, if the clustering criterion will be improved by .................. so. Nonparametric Procedures analysis techniques that are applicable only if the data are nonmetric (nominal or ..................). Nonprobability Sampling any sampling method where ............. probability of any population element's inclusion is .......... known, such as judgmental or convenience sampling. Nonresponse Bias an error due to the inability to elicit information from some respondents in a sample, often due to refusals. Nonresponse Error error that occurs due to nonparticipants of some eligible respondents in the study. This could be due to the unwillingness of the respondents to participate in the study or the inability of the interviewer to contact the respondents. Nonsampling Error error that is observed when a population is surveyed. Null Hypothesis the hypothesis to be tested. Observation a data collection method where the relevant behaviors are recorded; examples are direct observation contrived observation, physical trace measures, and behavior recording devices. Omission a memory error where a respondent leaves out an event or some aspect of it. Omnibus Survey a regularly scheduled personal interview survey comprised of questions from several separate firms. On-Air Test a test ad that is shown on a channel viewed at home. On-Line Telephone Interview an interview where the interviewer (1) reads the questions from an on-line cathode-ray-tube (CRT) terminal that is linked directly to a computer and (2) records the answers on a keyboard for entry to the computer. Open-Response/Unstructured Question a question with either no classification of responses or precoded classification of responses. Optimizing (in Cluster Analysis) a nonhierarchical method of clustering wherein the objects can later be reassigned to clusters on the basis of optimizing some overall criterion measure. Order Bias the bias of question responses due to the order of question presentation. Ordinal Scale a measurement that assigns only a rank order (i.e., "less than or greater than") to a set of objects. Paired Comparison Scale a scale in which the objects to be ranked are presented two at a time so that the respondent has to choose between them according to some criterion. Parallel Threshold a nonhierarchical clustering method wherein several cluster centers are selected simultaneously and objects within the threshold level are assigned to the nearest center. Threshold levels can be adjusted to admit fewer or more objects to the cluster. Parameter a number constant in each model considered, but varying in different models. Parametric Procedures analysis techniques that are applicable only if the data re metric (interval or ration). Partial Correlation Coefficient examining the association between a dependent and independent variable after satisfactorily factoring out the effect of other independent variables. Part-Worth Utilities utilities associated with particular product or brand attributes that are added together to obtain an overall utility for a product or brand alternative in conjoint analysis. Past Turning Point a point in time where a substantial change in growth rate can be identified by an environmental change; a forecast can be based on data since that point. Person Correlation Coefficient measures the degree to which there is linear association between two intervally scaled variables. Perceptual Map/Reduced Space a spatial representation of the perceived relationships among objects in a set, where the objects could be brands, products, or services. Periodic Discounting strategy adopted by firms wherein the firms can start at a high price and periodically discount their prices in order to draw consumers with lower reservation prices. This is useful when markets have consumers with differential reservation prices. Personal Interview a fact-to-face interview between the respondent and the interviewer. Phenotypic Sources of Refusal these pertain to why survey respondents refuse to participate on account of the characteristics of the data collection procedure such as which questions are asked, how they are asked, length of the interview, and so on. Phi-Suared a chi-square statistic corrected for sample size. Physical Trace Measures an observation method, such as a home audit, in which the natural "residue" or physical trace of the behavior is recorded. Pictorial Scales scales in which the various categories of the scale are depicted pictorially. Picture Interpretation a projective technique based on the Thematic Apperception Test (TAT), in which the respondent is asked to tell a story on the presentation of a series of pictures. Plus-One Dialing consists of selecting a random sample of telephone numbers from one or more telephone directories, then adding the constant "1" to the last four digits of each number selected. Population Standard Deviation true standard deviation of the population whose sample is being tested. Population Specification Error error that occurs when an inappropriate population is chosen for the study. Potential Rating Index Zip Markets (PRIZM) the classification and grouping or residents of zip code areas based on demographic and lifestyle data derived from the census. Predictive Validity criterion validity that is established by correlating the measurement score with a future criterion variable. Preexperimental Designs exploratory studies that have almost no control over the influence of extraneous factors on the results of the experiment. Pretest the presentation of a questionnaire in a pilot study to a representative sample of the respondent population in order to discover any problems with the questionnaire prior to full-scale use. Price Bundling the pricing strategy adopted for products that are nonsubstitutable, are perishable, and have an asymmetric demand structure. An example is pricing a car that includes many options. Price Signaling the pricing strategy adopted when the consumers in the market are willing to pay more for a product despite lack of knowledge regarding a product's quality. The firm produces an inferior product and sells it at the same price as the better quality product produced by another firm, in the hope that customers will associate high quality with high price. Primary Data data collected to address a specific research objective (as opposed to secondary data). Principal Components/Principal Factor Analysis a type of factor analysis that seeks to explain the greatest amount of variance in a data set, thus providing data reduction. Probability Sampling any sampling method where the probability of any population element's inclusion is known and is greater than zero. Problem or Opportunity Definition a process of understanding the causes and predicting the consequences of problems or a process of exploring the size and nature of opportunities; the second phase of marketing program development. Profile Analysis the comparison of evaluations of the alternatives in a consideration set, on the important and determinant attributes. Program Evaluation and Review Technique (PERT) probability-based scheduling approach that recognizes and measures the uncertainty of project completion times. Programmatic Research research performed to develop marketing options through market segmentation, market opportunity analysis, or consumer attitude and product usage studies. Projective Techniques a set of presentation methods of ambiguous, unstructured objects, activities, or persons for which a respondent is asked to give interpretation and find meaning; the more ambiguous the stimulus, the more the respondent has to project him or herself into the task, thereby revealing hidden feelings, values, and needs; examples are word association, role playing, completion tests, and picture interpretation. Proportional Stratified Sampling sampling procedure in which the number of objects or sampling units chosen from each group is proportional to the number in the population. Purchase Interception Technique (PIT) a consumer survey technique for collecting data through personal interviews by in-store observation of purchase behavior and then interception of consumers in the shopping environment to determine the reasons behind that behavior. Qualitative Research research designed primarily for exploratory purposes, such as getting oriented to the range and complexity of consumer activity, clarifying the problem, and identifying likely methodological problems; examples are individual and group interviews, projective techniques, and case studis. Quasi-Experimental Design offers the researcher some degree of control, but there is no random assignment of subjects as there is for true experimental designs. Quick Clustering one method of cluster analysis. Quota Sampling a judgmental sampling method that is constrained to include a minimum from each specified subgroup in the population. Random-Digit Dialing nondirectory procedure for selecting all 10 telephone number digits at random. Random Error measurement error due to changing aspects of the respondent or measurement situation. Randomization a procedure in which the assignment of subjects and treatments to groups is based on chance. Randomization ensures control over the extraneous variables and increases the reliability of the experiment. Randomized Block Design an experimental design in which the test units first are grouped into homogeneous groups along some prespecified criterion and then are assigned randomly to different treatments within each block. Rank-Order Scale a scale in which the respondent is required to order a set of objects with regard to a common criterion. Ratio Scale a measurement that has a true or meaningful zero point, allowing for the specification of absolute magnitudes of objects. Ratio-Scaled Data interval type data that has a distinct zero level. Reading-Habit Method measuring print media exposure by asking how many issues of the last four you have read. Recent-Reading Method measuring print media exposure by asking whether someone looked at a copy in the past week for a weekly or in the past month for a monthly. Recording Error error that occurs due to the improper recording of the respondents' answers. Refusal Rate a measure of any data collection method's ability to induce contacted respondents to participate in the study. Refusals a source of nonsampling error caused by a respondent's refusing to participate in the study. Regression Analysis a statistical technique that develops an equation that relates a dependent variable to one or more independent (predictor, explanatory) variables. Relationship Marketing establishing, developing, and maintaining long-term, trusting relational exchanges with valued customers, distributors, suppliers, and dealers by promising and delivering high-quality services and products to the parties over time. Relative Market Potential the market potential of one segment relative to other segments. Relevance a criterion used to judge whether a market research study acts to support strategic and tactical planning activities. Reliability the random error component of a measurement instrument. Research Approach one of the following six sources of data–the information system, secondary and standardized data sources, qualitative research, surveys, observation and experiments. Research Boundary a delineation of the scope of the research study in terms of items such as population characteristics locations, and product markets. Research Design detailed blueprint used to guide a research study toward its objectives. Research Objectives a precise statement of what information is needed, consisting of the research question, the hypotheses, and the scope or boundaries of the research. Research Process the series of stages or steps underlying the design and implementation of a marketing research process including the establishment of the research purpose and objectives, information value estimation, research design and implementation. Research Proposal a plan for conducting and controlling a research project. Research Purpose the shared understanding between the manager and the researcher regarding the decision alternatives, the problems and opportunities to be studied, and who the users of the results shall be. Research Question the statement(s) of what specific information is required for progress toward the achievement of the research purpose. Research Tactics the development of the specific details of the research, including the research approach, sampling plan, and choice of research suppliers. Response Bias the tendency of respondents to distort their answers systematically for a variety of reasons, such as social desirability and prestige seeking. Response Error error that occurs due to the respondents providing inaccurate information (intentionally or unintentionally). This might be due to the inability of the respondent to comprehend the question or a misunderstanding of the question due to fatigue or boredom. Response Style the systematic tendency of respondents to select particular categories of responses regardless of the content of the questions. Retail Store Audits audit data collected by research firms whose employees visit a sample of stores at fixed intervals for the purpose of counting stock and recording deliveries to estimate retail sales. Role-Playing a projective technique in which the respondent assumes the role or behavior of another person so that the respondent may reveal attitudes by projecting him or herself fully into the role. SAMI/Burke makes available standardized and recurrent marketing research reports to subscribers, usually manufacturers of frequently purchased consumer packaged goods. Sample a subset of elements from a population. Sampling process of surveying only a sample of the whole population to make inferences about the population. Sampling Efficiency/Efficiency of Sampling ratio of accuracy over cost. Sampling Equivalence deals with the question of identifying and operationalizing two comparable populations and selecting samples that are representative of other populations and that are comparable across countries. Sampling Error error that occurs if the difference in value (error) between the population parameter and the sample statistic is only because of sampling. Sampling Frame a listing of population members that is used to create a random sample. Sampling Frame Error error that occurs when the sample is drawn from an inaccurate sampling frame. Sampling Unit any type of element that makes up a sample, such as people, stores, and products. Scale Transformation manipulation of scale values to ensure comparability with other scales. Scanner Data the scanner is a device that reads the universal product code from a package as it is processed at a retailer's checkout stand. Scanner data include data on all transactions including size, price, and flavor. They also normally include in-store information such as special displays. Scatter Diagram a two-dimensional plot of two variables. Scree Plot used in factor analysis, a plot of the eigenvalues against the number of factors in order of their extraction. The shape of the plot is used to determine the number of factors. Screening Sample a representative sample of the population being studied that is used to develop or pretest measurement instruments. Seasonal Index a representation of the seasonal forecast. Secondary Data data collected for some purpose other than the present research purpose. Second Market Discounting a pricing strategy wherein the firm discounts its prices in the other markets below its average cost. Selection Bias differences among subjects, prior to an experiment, that affect the experimental results. Selection Error error that occurs in a nonprobability sampling method when a sample obtained is not representative of the population. Selective Research research done to test different decision alternatives. Sell-In Test Market the new product being tested must be sold to the retailer. Shelf space is not prearranged. Semantic-Differential Scale a scale in which the respondent is asked to rate each attitude object in turn on a five or seven point rating scale bounded at each end by polar adjectives of phrases. Semistructured/Focused Individual Interview a type of individual depth interview in which the interviewer attempts to cover a specific list of topics or subareas. Sensitivity the ability of a measurement instrument to discriminate among meaningful differences in the variable being measured. Sequential Sampling a sampling method in which an initial modest sample is taken and analyzed, following which, based on the results, a decision is made regarding the necessity of further sampling and analysis; this continues until enough data are collected. Sequential Threshold a nonhierarchical clustering method wherein a cluster center is selected and all objects within a prespecified threshold value are grouped. Then a new cluster center is selected and the process is repeated. Once objects enter a cluster they are removed from further processing. Significance Level the probability of obtaining the evidence if the null hypothesis were true. Similarity/Judgment the judgment an individual makes about whether two objects are similar or different without specifying specific attributes. Simple Random Sampling a sampling method in which each population member has an equal chance of being selected. Single Linkage linkage procedure that is based on the shortest distance between objects to form clusters. Single-Source Data data on product purchases and causal factors such as media exposure, promotion influence, and consumer characteristics that come from the same households as a result of advances in scanner and information technology. Situation Analysis the stage of the market planning process that deals with understanding the environment and the market, identifying opportunities and threats, and assessing the firm's competitive position. Snowball Sampling a judgmental sampling method in which each respondent is asked to identify one or more other sample members. Social Indicators statistical series that describe trends in social rather than economic variables. Split-Ballot Technique the inclusion of more than one version of a question in a questionnaire. Split-Cable Testing exposing two or more groups of a cable system to different ads and monitoring their purchases. Spurious Association an inappropriate causal interpretation of association due to an unmeasured variable influencing both variables. Standard Deviation the square root of the variance. Standard Error of Estimate in regression analysis, the standard deviation of the sampling distribution of the regression model parameter estimates. Standard Industrial Classification (SIC) System a uniform numbering system developed by the U.S. Government for classifying industrial establishments according to their economic activities. Standard Metropolitan Statistical Area (SMSA) census tracts that are combined in counties containing a central city with a population of at least 50,000. Standardized Marketing Data Sources external sources of marketing data collected by outside organizations for several information users who have common information needs. Stapel Scale a 10-category, unipolar rating scale with categories numbered from -5 to +5. It modifies the semantic differential by having the respondent rate how close and in what direction a descriptor adjective fits a given concept. Statistic any of several characteristics of a sample. Statistical Control the control of extraneous variables through statistical mehtods. Statistical Designs designs that allow for examining the effects of different treatment levels of an experimental variable, and also the effects of two or more independent variables. Strategic Plans plans than focus on strategic decisions of resource allocation with long-run performance implications, usually having time horizons of more than one year. Stratified Sampling a sampling method that uses natural subgroups or strata that are more homogeneous that the total population. Surrogate Information Error error that occurs due to the difference between the information that is required for a marketing research study and the information being sought by the researchers. Survey Method a method of data collection, such as a telephone or personal interview, a mail survey, or any combination thereof. Syndicated Services services from firms such as A. C. Nielsen and Information Resources Inc., where costs are shared by multiple client firms. Systematic Error the measurement error due to constant aspects of the person or measurement situation. Systematic Sampling sampling that involves systematically spreading the sample through the list of population members. Test marketing the introduction of the new product in selected test cities that represent the typical market, so that the results of the performance in these markets can be projected on a national basis. Third-Person Techniques a technique of ascertaining the respondents' views by asking them to answer for a third person. Through-the-Book measurement of exposure to print media by asking respondents if they recognized articles in an issue. Thurstone/Equal-Appearing Interval Scale a scale developed by first having a group of judges categorize a set of items and then selecting those items that were similarly categorized; the scale is administered by having respondents choose those statements with which they agree. Time Series Design design in which a series of measurements is employed during which an experimental treatment occurs. Times-Series Forecasting data collected over time, such as weekly sales data for three years; especially effective for short-term forecasting. Top-Down/Chain-Ratio Approach a method of determining market potential that has as its starting point the identification of the total and available markets. Total Quality Management the concept of creation of value to the consumer through enhanced product and service quality, thereby enhancing customer satisfaction. Tracking Studies monitoring the performance of advertising by regular surveys of the audience. Trade-Off Approach a method of collecting data for trade-off analysis in which the respondent is asked to rank each combination of levels of two attributes from most preferred to least preferred. True Experimental Designs experimental designs that adopt the random assignment procedure. Type I Error rejecting a null hypothesis when it is true. Type II Erro accepting a null hypothesis when it is false. Unaided Recall a questioning approach in which the respondent is asked to remember an object of interest without the assistance of clues from the researcher. Uniform Product Code (UPC) a standard code assigned to each manufacturer's brand and pack size so that its purchases can be tracked through a store scanner system. Uniform Resource Locator (URL) the address of a Web site on the World Wide Web or a general-purpose Internet addressing protocol in WWW (http). U.S. Bureau of the Census the Federal agency that conducts the U.S. Census once every 10 years and complies demographic statistics on the population. It also conducts one show surveys for other federal agencies. Use Test a type of product evaluation where the product is given to consumers; after a reasonable period of time, the consumers are asked for their reactions to it. Utility in Trade-off Analysis the worth or value of each level of each attribute relative to the other levels. Validity the ability of a measurement instrument of measure what it is supposed to measure. Values and Lifestyles Survey (VALS) a survey conducted by the stanford Research Institute, which classified the U.S. population into nine lifestyle segments based on individual values and lifestyles of survey respondents. Variable Respecification a procedure by which existing data are modified to create new variables or a large number of variables are collapsed into fewer variables. Variance a measure of dispersion based on the degree to which elements of a sample or population differ from the average element. Varimax Rotation a rotation method that searches for simple structure; a pattern of factor loadings where some loadings are close to one, and some loadings are close to zero. Ward's Method method based on the loss of information resulting from grouping objects into clusters, as measured by the total sum of squared deviations of every object from the mean of the cluster to which the object is assigned. Warehouse Withdrawal Services syndicated services offered by firms such as SAMI/Burke in which periodic audits are done at the warehouse or wholesale level and reports are produced on product shipments made to retail stores served by those warehouses. Weighting a procedure by which each response in the database is assigned a number according to some prespecified rule. Within-Treatment Variance variance in the response variable within a single treatment level. Word Association a projective technique in which the respondent is asked to give the first word that comes to mind on the presentation of another word. World Wide Web a graphical environment that provides point-and-click access to the Internet through a network of World Wide Web servers.