Research Design BUS ADM 462: Marketing Research I-Hsuan (Shaine) Chiu
Learning Objectives • Learn different types of research approaches commonly used in marketing research • Describe the three basic types of research design • Understand the concepts and the emphasis of these three types of research design
Research Design • A master plan specifying the approaches that will be used to collect and analyze the information needed to meet research objectives
Research Design • “Good” research design ensures… • All of the necessary information will be obtained • The Information collected will be relevant and useful to management • The marketing research project will be conducted effectively and efficiently
Exploratory Research • Goals • To provide a better understanding of a situation • Produce hypotheses about what is going on in a situation • Help define the research problem(s) • When? • Realize a problem exists, but does not yet understand why • How? • Anything that works! • Secondary data analysis, case analysis, in-depth interviews, focus groups • Findings • Tentative, not conclusive • Provide directions to more formal, conclusive research
1. Secondary Data Analysis • Secondary data • Data have previously been gathered by someone other than the research and/or for some other purpose than the research project at hand • Secondary data analysis • The process of searching for and interpreting existing information relevant to the research topic • The quickest and cheapest approach to discover hypothesis • Example: • Industry publications • Census data published by the government • Internet
2. Case Analysis • A review of available information about one or more former situations to gain understanding of a current research problem with similar characteristics • Useful technique for • Using organizations that excel at some function as sources of ideas for improvement • Developing strategies to prevent and manage crises • Example: • Improving the productivity of sales force
3. In-Depth Interviews • An unstructured, direct, personal interview in which a single respondent (i.e., one on one) is probed by a highly skilled interviewer to uncover underlying motivations, beliefs, attitudes, and feelings on a topic • Unique advantage: can uncover hidden issues that may not be shared in a group setting • Underlying motives, beliefs, and attitudes • Sensitive topics
3. In-Depth Interviews • When to Use In-Depth Interviews? • Detailed probing of the respondent • Discussion of confidential, sensitive, or embarrassing topics • Situations where strong social norms exist • Detailed understanding of complicated behavior • Interviews with professional people • Interviews with competitors, who are unlikely reveal the information in a group • Situations where the product consumption experience is sensory in nature, affecting mood states and emotions
4. Focus Groups • Small groups of people brought together and guided through an unstructured, spontaneous discussion for the purpose of gaining information relevant to the research problem
4. Focus Groups • Advantages • Generate fresh ideas • Allow clients to observe their participants • May be directed at understanding a wide variety of issues • Allow fairly easy access to special respondent groups • Disadvantages • Participants are not representative samples • Success greatly depends on the ability of the moderator • Results can be difficult to interpret
4. Focus Groups • Factors to consider when conducting a focus group • Group size • Usually 6-12 participants • Group composition • Homogeneous respondents within a group • Can be different between groups • Location and environmental setting • Interview time • Recording • Reporting and analyzing results • Not representative of the general population • Moderator • Creating an atmosphere that is conductive to openness • Making sure respondents focus on study
In-Depth Interviews vs Focus Groups (‘+’ indicates ‘relative advantage’ / ‘–’ indicates ‘relative disadvantage’)
Causal Research • Goals • To obtain evidence regarding “cause-and-effect” relationships • When? • When managers need stronger evidence that a particular action is likely to produce a particular outcome • When need to test cause-and-effect relationships • How? • Experiments • Findings • Conclusive
5. Experiments • A type of study in which one or more independent variables (X) are manipulated to see how one or more dependent variables (Y) are affected, while also controlling the effects of additional extraneous variables ? X Y Does change in X cause change in Y? Price, advertising, packaging design, etc. Sales, perceptions, awareness, interest, etc.
5. Experiments • Independent variable (X) • Variables over which the researcher or the marketer has control and wishes to manipulate • Dependent Variable (Y) • Variables that are measured in response to changes in independent variables
5. Experiments • Correlation ≠ Causality!!! • The correlation observed between A and B does not imply “A causes B” • B causes A • Eg. Healthier men are more likely to get married • Third factor C causes both A and B • Short-sighted parents are more likely to leave the light on and have short-sighted kids
5. Experiments • The Validity of Experiments • Internal validity (Was the experiment done right?) • The degree to which the observed change in the dependent variable (Y) is actually due to the independent variable (X) • External validity (Is the result generalizable?) • The extent to which the results of the experiment can apply to the “real world” How valid is this experiment? How believable is this experiment?
5. Experiments Laboratory Experiments Field Experiments Experiments conducted in their natural setting Eg. A retail store Control of variables other than X or Y is challenging Store conditions vary X variables are manipulated • Experiments conducted in a contrived, artificial setting • Eg. a chemistry lab • Control of variables other than X or Y is maximized • Labs are sterile • X variables are manipulated
5. Experiments • Experiment – A/B Testing • A randomized experiment that tests two alternatives to see which one performs better
5. Experiments • Example – Test Markets • Experiments conducted in a field setting to evaluate a new product or service or other elements of the marketing mix
5. Experiments • Types of Test Markets
Descriptive Research • Goals • To describe the market characteristics or behaviors • When? • Clear statement of the problem, specific hypotheses, and specification of the information needed • How? • Data is collected in a structured manner, typically using large, representative samples • Conduct quantitative analysis • Findings • Used to make generalizations about the target market
6. Cross-Sectional Studies • Example: Which political party do you support? 1 = Democrat 2 = Republican 3 = Independent Person 1980 1984 1988 1992 #1 1 1 3 3 #2 1 1 1 3 #3 3 3 2 2 : #1000 2 2 2 3 Cross-Sectional Variation
6. Cross-Sectional Studies • A type of study that measures units from a sample of the population at one point in time • Example: 2016 Presidential Election Polls
7. Longitudinal Studies • Example: Which political party do you support? 1 = Democrat 2 = Republican 3 = Independent Person 1980 1984 1988 1992 #1 1 1 3 3 #2 1 1 1 3 #3 3 3 2 2 : #1000 2 2 2 3 Longitudinal Variation
7. Longitudinal studies • A type of study that repeatedly measures the same sample units of a population over a period of time • Example: National Consumer Panel • Panel: a group of respondents who have agreed to provide information at regular intervals
7. Longitudinal Studies • Types of Panels
7. Longitudinal Studies • Continuous Panel Example – Brand Switching Matrix • Two cross-sectional studies: 500 UWM students What is the market share for A, B and C in March, respectively? What about April?
7. Longitudinal Studies • Continuous Panel Example – Brand Switching Matrix • Two cross-sectional studies: 500 UWM students Can we say A lost 25 customers to C? B did not gain or lose any customers?
7. Longitudinal Studies • Continuous Panel Example – Brand Switching Matrix • Continuous Panel – 500 UWM students
7. Longitudinal Studies • Continuous Panel Example – Brand Switching Matrix • Continuous Panel – 500 UWM students • How many students bought A in March? • How many students bought A in April? • How many students bought A both in March and April? • What is A’s market share in March and April?
7. Longitudinal Studies • Continuous Panel Example – Brand Switching Matrix • Continuous Panel – 500 UWM students • How many students who bought A in March switched to B in April? • How many students who bought C in March switched to Ain April? • How many customers did A gain in April? How many did A lose?