2 Descriptive and Causal Research Designs Quantitative methods of collecting primary data that involve larger samplesPrimary method is the survey, but other methods are possible.
3 Descriptive Research Designs Describing something with data (as opposed to showing a cause-effect relationship).Example: Creating a segment profile (age, income, education levels, typical purchases of segment)Description goals must be clear at the outset unlike exploratory researchMuch of marketing research is descriptiveNo “manipulations”Cannot prove causality
4 Survey MethodsSurvey research methods: Research procedures for collecting large amounts of data using question-and-answer formatsGoals of Survey Research:Make accurate predictions about relationships between market factors and behaviorsGain insights into understanding the relationships between variables and differences between groupsVerify or re-validate existing relationships
5 Advantages and Disadvantages of Survey Research Designs
6 Types of Errors in Surveys Sampling errorsThe difference between the findings based on the sample and the true values for a populationCaused by:(1) the method of sampling used, and(2) the size of the sampleCan be reduced by:Increasing sample sizeUsing the appropriate sampling method
7 Non-sampling Errors Respondent Errors Nonresponse Error Response Error Consist of both nonresponse error and response errorNonresponse ErrorA systematic bias that occurs when the final sample differs from the planned sample due a systematic failure to respond by a segment of targeted sampling elements (occurs before survey administration).Response ErrorWhen respondents have impaired memory or do not respond accurately (occurs during survey administration).
9 Advantages and Disadvantages of Person-Administered Surveys
10 Advantages and Disadvantages of Self-Administered Surveys
11 Selecting the Appropriate Survey Method Situational characteristicsBudgetCompletion time frameQuality requirementsCompleteness of dataData generalizability: How projectable to the population is the sample data?Data precision
12 Selecting the Appropriate Survey Method Task characteristicsTask difficultyRequired stimuliAmount of information asked from respondentsTopic sensitivity: The degree to which a survey question leads the respondent to give a socially acceptable response
13 Selecting the Appropriate Survey Method Respondent characteristicsDiversityIncidence rate: The percentage of the general population that is the subject of the market researchRespondent participationAbility to participate: The ability of both the interviewer and the respondent to get together in a question-and-answer interchangeWillingness to participate: The respondent’s inclination or disposition to share his or her thoughtsKnowledge level: Degree to which the selected respondents feel they have knowledge of or experience with the survey’s topics
14 Causal Research Designs Causal research: Studies that enable researchers to assess “cause-effect” relationships between two or more variablesIndependent variables: Variables whose values are directly manipulated by the researcherDependent variables: Measures of effects or outcomes that occur as a result of changes in levels of the independent (causing) variable(s)
15 Causal Research Designs Researchers use experimental designs in causal researchExperiment: An empirical investigation that tests for hypothesized relationships between dependent variables and manipulated independent variablesTest and control casesWhat do we mean by “manipulated” variables?Discrete vs. continuous variablesLevels of a variable
16 The Nature of Experimentation Experiments can show and explain cause-and-effect relationships between variables and/or constructs.Variable: A measurable element that can vary or have more than one valueExamples: Age, Gender, IncomeConstruct: A collection of variables which, when measured and analyzed as a group (i.e. using a scale or multiple scales), produce a meaningful super-ordinate variableExamples: Intelligence, Brand Loyalty, Satisfaction
17 The Nature of Experimentation Control variables:Not usually as important as the main IVs to the researchAffect the DV but (ideally) not the IVsAre often used as segmentation variables in marketing researchExtraneous variables: Any variables that experimental researchers do not measure or control that may affect the dependent variable (if it does affect the DV, it is called a Confounding Variable)
18 Validity Concerns with Experimental Research Validity: The extent to which the conclusions drawn from an experiment are trueInternal validity: Extent to which the research design accurately identifies causal relationships (example: Does our study reveal consumers’ true preferences?)External validity: Extent to which a causal relationship found in a study can be expected to be true for the entire target population (example: Are the “true” preferences uncovered by the experiment representative of the entire target market’s preferences?)
19 Reliability Concerns with Experimental Research Reliability: The extent to which the research instrument yields the same or similar outcomes on repeated usage occasionsExample:Reliable GMAT scores for someone: 650, 640, 650Unreliable GMAT scores for someone: 650, 750, 450Measured by Split-half Reliability Coefficient or Chronbach’s Alpha CoefficientExperiments must be both valid and reliable in order for their conclusions to be trustworthy.
20 Comparing Laboratory and Field Experiments Laboratory (lab) experiments: Causal research designs conducted in an artificial settingField experiments: Causal research designs conducted in a natural or “real” settingIVs can be manipulated in either alternative, but it is much easier to do so in lab experiments.
21 Test MarketingUsing controlled field experiments to gain information on specified market performance indicatorsMost common type of field experimentUsed to help launch new products or develop new marketsProblems with competitive interferenceDon’t neglect generalizability (i.e. external validity) concerns