BA 591:  Issues in Consumer Research Methods

SPRING 2006

Click here for PDF of Syllabus

Wednesday, 8:45-11:45 AM, Fuqua Academic Center, Conference Room 14

Professors Gavan Fitzsimons and John Lynch
Offices A327 Faculty Building & A324 Faculty Building, Fuqua School of Business
Phones 660-7793, 660-7766
Fax 660-3730
E-Mail gavan@duke.edu, john.lynch@duke.edu
Admin Assistant Nancy Gump , 660-7838

This course is designed to introduce you to issues of research design as they apply to behavioral research in marketing, consumer behavior, and to social science research in general. We will discuss how to plan, design, conduct, and interpret experimental and observational research in marketing and consumer behavior. We will also read a little bit of philosophy of science. The ability to conduct research competently and to publish it in academic journals is a key determinant of your success in a doctoral program and in your future academic career.

Knowledge of the "theory" of performing research and practical experience are both needed to develop research skills. In this course, you will read articles and books chapters describing how research should be done including the identification of research problems, the development of theories addressing these problems, the design of studies to test theories, and the interpretation of research results. You will be required to apply this information about the research process and experience the practical considerations that arise in each step of the research process.

The content of the research discussed in this course need not be restricted to consumer behavior and marketing. The course is appropriate for any behaviorally oriented researchers in other fields of business and social science. Our mode of class discussion will rely on each of you relating the course material to issues and problems in your areas of interest.

Class participation is expected in quantity and quality. Course grades will be calculated using the following weights:

Short Paper Assignments

20%

Measurement Project

15%

Class Participation

30%

Mid Term Exam

15%

Final Paper

30%

Assignments should be submitted by email to our assistant, Nancy Gump ( ngump@duke.edu ) – cc us in case Nancy happens to be out of the office on the due date. Please start the SUBJECT of any course-related message with the string “BA591” (CAPS, no spaces), so Nancy (& we) can automatically suck those messages into a folder. You'll submit those assignments the afternoon before class, and Nancy will paste your answers into a single document for discussion in class.

Text

We are using a collection of chapters and articles from various sources, but we are reading the first 6 chapters of:

Shadish, Cook, and Campbell, (2002), Experimental and Quasi-Experimental Designs for Generalized Causal Inference.  Boston:  Houghton Mifflin.  We’ll start using this in Session 5.  Here’s a link from Amazon.  We have not placed an order at the bookstore.

Measurement Assignment

One of the key skills from the course is how to devise a reliable and valid measure of some concept. Beginning in session 2, we will define a concept (perhaps “consumer disgust”, or “propensity to plan use of time or money” or “product convenience”). We will operationalize it in the form of a multi-item scale, determine what related concepts it must be discriminated from, determine where it fits in some theoretical network of antecedents and consequences, construct a questionnaire to measure our focal concept and these related concepts, administer the questionnaire to a small sample of respondents, analyze the data to purify our measure and to provide evidence of its reliability and validity. You will write up your final analyses in pairs. These activities will be distributed over sessions 2 through 7 of the course, as shown below.

Session

Homework

In Class

2.  Jan 24

Concepts & measurement

Generate conceptual definition, write 4 items

Agree on consensus definition, including subdimensions

3. Jan 31

Trait validity

From superset of items, classify as pertaining to subdimensions, choose best 4 exemplars of each 

Use answers to Q13 to agree on constructs for discriminant validity

4. Feb. 7

Construct validity & nomological net

Write items for discriminant validity constructs

Reword items from Session 3.

Generate nomological net of antecedents and consequences.

Write 3 items for each related construct.

Agree on consensus nomological net. 

Post-class, I distribute questionnaire. 

Email any corrections. Questionnaire goes out on Friday.

5. Feb. 14

Causal Research + validity types

Collect data from 10 respondents over weekend before session 5.

Discuss analysis of data from past year’s example.

6. Feb. 21

Quasi-experiments

Work on data analysis

Answer questions about measurement assignment data analysis

7. Feb 28

Moderators & mediators

Measurement assignment analysis due.  We strongly recommend that you do most analysis before session 6.

  

Final Paper

You have two options for a final paper. 

  1. Analysis of methodological issues in your own research.  The first is to take a current research project (your first year paper, a collaborative project with a faculty member, or piece of empirical behavioral research you are doing.  Write a) a 3-5 page Introduction that explains the research problem and lays out your hypotheses, b) a Method section for the paper, c) an “Expected Results” section that explains the analyses you plan to do and the expected pattern of results, and d) a concluding section on “Methodological Choices” that explains what decisions you are having to make about method and how you used the concepts from class to make those decisions.  The entire paper should be about 15 pages, double-spaced.  I will be evaluating you most heavily on d) – i.e., on the insight with which you apply our class concepts to move your own research forward.  I do not want this to be a make-work paper at all.  It should advance your progress on a paper you hope to publish eventually.  (This is our much-preferred option.)
  2. Meta-analytic literature review in your own research area.  Some students in the class may not have a study they are now working on.  If you are only at the literature review stage, you can write a meta-analytic review, following the methods described in Session 10,  Rosenthal & Rubin Ch. 22.  If you choose this option, you should read more about meta-analysis, following references I will give you upon request.

Papers are due on the Friday at noon after the last day of class – i.e., on Friday, April 20th.

Readings will be passed out each week as pdfs. If you have any problems with the readings, please contact our assistant, Nancy Gump (ngump@duke.edu) or 660-7838. Her desk is right outside of John's office.

Room:

All meetings will be on Wednesday, from 8:45 AM- 11:45 AM in the Conference Room 14 in the Fuqua School of Business (at the bottom of the circular stairs in the Fox Center).

Schedule of readings:

In the schedule of assigned readings that follows, required readings are listed in italics.  Optional readings are in normal type face, preceded by a plus (+).  Please bring these readings to class too. I won’t expect that you have prepared them, but will refer to specific sections, tables, and figures from those articles in class. 

Class 1

Date

Topic

Readings

Wed, Jan.  17

The Scientific Method

Delayed start until week 2 of semester

Problems, Hypotheses, and Theories

1. Rosenthal, Robert and Ralph Rosnow (1991) Essentials of Behavioral Research:  Methods and Data Analysis  (New York:  McGraw Hill.)  Read Ch. 1, pp. 3-25, “The Nature of Behavioral Research”

2. Kerlinger, Fred (1986), Foundations of Behavioral Research, 3rd Edition. Orlando, FL: Harcourt Brace & Company, Read Ch 2, pp 15-25. “Problems and Hypotheses”

3. Rosenthal and Rosnow, Ch. 2, Development and Testing of Research Ideas, pp. 26-28 and pp. 31--35 only.

Please prepare the questions in this linked document.

Class 2

Date

Topic

Readings

Wed, Jan.  24

Concepts, Constructs, and Measurement

Scales of Measurement

Common Types of Measures

Content Analysis

+Distributed but not assigned. We ’ll lecture about papers 5-6 and their connection to our other readings

1. Rosenthal and Rosnow, Ch. 2, Development and Testing of Research Ideas, 35--38 only (“Defining Terms”).

2. Nunnally, Jum and Ira Bernstein, Psychometric Theory (3rd Edition), New York: McGraw-Hill, 1994. Read Ch. 1, “Introduction”, pp. 3-30.

3. Aronson, Elliot, Phoebe Ellsworth, J. Merrill Carlsmith, and Marti Gonzolez, Methods of Research in Social Psychology (2nd Edition). New York: McGraw-Hill, 1990. Read Ch. 8, “The Dependent Variable,” pp. 240-248,(Intro) pp. 251-253 (Likert Scales), pp.255-257 (Semantic Differential Scales) pp. 263-271 (Verbal Measures, Behavioral Measures) pp. 280-291 (Reliability and Validity).

4. +Smith, Charles P. (2000), “Content Analysis and Narrative Analysis” in Reis and Judd (Eds.) Handbook of Research Methods in Personality and Social Psychology. Cambridge: Cambridge University Press, pp. 313-335 Read pp 313-327 on Content Analysis. Don’t read.

5. +McCorquodale, Kenneth. and Paul Meehl, “On a Distinction between Hypothetical Constructs and Intervening Variables,” Psychological Review, 1948, 55, 95-107. Don’t read.6. +Bakeman, Roger (2000), “Behavioral Observation and Coding,” in Harry T. Reis and Charles M Judd (Eds.) Handbook of Research Methods in Personality and Social Psychology. Cambridge: Cambridge University Press, pp. 138--159. Don’t read

Class 3

Date

Topic

Readings

Wed,
Jan 31

Measurement Error and Reliability

Construct Validity as Trait Validity

Construct validity; How inappropriate pooling and restriction of range affect revealed associations.

1.Nunnally and Bernstein, Ch. 5.  “Linear combinations, partial, and multiple combinations” Read pp. 159-163 on linear combinations only.  We will read other parts of this chapter in Week 4.

2. Peter, J. Paul (1979), “Reliability: A Review of Psychometric Basics and Recent Marketing Practices,” Journal of Marketing Research, 16 (February), 6-17. Read pp 6-10. Do not read pp. 11-17.

3.Churchill, Gilbert A., Jr. (1979), “A Paradigm for Developing Better Measures of Marketing Constructs,” Journal of Marketing Research, 16 (February), 64-73

4.Nunnally and Bernstein, Ch. 3 "Validity" 83-113.
Articles 5-8 are distributed but not assigned. I will lecture about these in class. Do not read these articles, but please bring to class.

Multitrait multimethod

Matrix to assess trait validity

Example of a study to validate a measure of a construct

Cause v. effect indicators

Testing whether a multi-item scale is unidimensional

5. +Campbell, Donald T. and Duncan W. Fiske (1959), “Convergent and Discriminant Validation by the Multitrait Multimethod Matrix,” Psychological Bulletin, 56, 81-105.

6.+Peck, Joann and Terry L. Childers (2003), “Individual Differences in Haptic Information Processing: The "Need for Touch" Scale,” Journal of Consumer Research, 30 (December), 430-442. Nice example of measure development. We’ll use this example in as application of articles 1-4.

7. +Bollen, Kenneth and Richard Lennox (1991), "Conventional Wisdom on Measurement: A Structural Equation Perspective," Psychological Bulletin, 110, 305-314.

8. +Gerbing, David and James Anderson (1988), "An Updated Paradigm for Scale Development Incorporating Unidimensionality and Its Assessment," Journal of Marketing Research, 25, 186-192.

Class 4

Date

Topic

Readings

Wed,
Feb. 7

Construct Validity as Nomological Validity: The meaning of a construct is given by its relations to other variables in a nomological network.

+ = Reference for further study after class. Do not read.

Zero-Order and Partial Relationships

1. Cronbach, Lee J., and Paul Meehl (1955), “Construct Validation in Psychological Tests,” Psychological Bulletin, 1955, 52, 281-302.

2. +Campbell, Donald T. (1960), “Recommendations for APA Test Standards Regarding Construct, Trait, or Discriminant Validity,” American Psychologist, 15, 546-553.

3. Babbie, Ch. 16.  “The Elaboration Model”, pp. 388-403.

4. Nunnally and Bernstein, Ch. 5.  “Linear combinations, partial, and multiple combinations” Read 175-180 on partial correlation.  Don’t read the rest of this chapter.

Class 5

Date

Topic

Readings

Wed, Feb. 14

Causal Research

The Concept of Cause

Threats to Valid Causal Inferences

1. Aronson, Ellsworth, Carlsmith, and Gonzales (1990), Methods of Research in Social Psychology (2nd Edition).  Reading, MA: McGraw-Hill.  Read “Introduction” pp. 1-7, and SKIM Ch. 1, “An Introduction to Experiments,”  pp. 8-39.

2. Shadish, Cook, and Campbell, (2002), Experimental and Quasi-Experimental Designs for Generalized Causal Inference.  Boston:  Houghton Mifflin.  Read Ch. 1, “Experiments and Generalized Causal Inference (pp. 1-32)

3. Shadish et al (2002), Ch. 2, “Statistical Conclusion Validity and Internal Validity”  Read pp. 33-42 “Validity”, p. 52 “The problem of Accepting the Null Hypothesis”, and pp. 53-63, “Internal Validity, The Relationship between Internal Validity and Statistical Conclusion Validity”

4. Shadish et al. (2002), Ch. 3.  Construct Validity and External Validity”.

Class 6

Date

Topic

Readings

Wed,
Feb 21

External Validity

Student subjects

JCR External Validity Debate

17 Years later

+ = Reference for later study, included here for completeness

Meta-analysis

1.  Mook, D. G. (1983). In defense of external invalidity. American Psychologist, 38, 379-387.

2. Sears, D. O. (1986). College sophomores in the laboratory: Influences of a narrow database on social psychology’s view of human nature. Journal of Personality and Social Psychology, 51, 515-530.

3. Ferber, Robert (1977) “Research by Convenience” Journal of Consumer Research, 57-58.

4. Calder, Bobby J., Lynn W. Phillips, and Alice M. Tybout (1981), “Designing Research for Application,” Journal of Consumer Research, 8, 197-207.

5. Lynch, John G., Jr. (1982), “On the External Validity of Experiments in Consumer Research,” Journal of Consumer Research, 9, 225-239.  (Erratum 1983 JCR, p. 455.)

6. Lynch, John G., Jr. (1999), “Theory and External Validity,” Journal of the Academy of Marketing Science, 27 (Summer), 367-376. 

7. +Hutchinson, J. Wesley, Wagner A. Kamakura, and John G. Lynch, Jr. (2000), “Unobserved Heterogeneity As An Alternative Explanation for ‘Reversal’ Effects in Behavioral Research.” Journal of Consumer Research,27 (December), 323-344.

8. Rosenthal and Rubin, Ch. 22, “Meta-Analysis: Comparing and Combining Results,” pp. 491-512.

Class 7

Date

Topic

Readings

Wed, Feb 28

Quasi-Experimental Design

 

 

 

Not assigned, but to be presented by student

1. Aronson, Ellsworth, Carlsmith, and Gonzales, Ch. 5, “Alternatives to the Controlled Experiment”,  157-182.

2. Shadish, Cook, and Campbell, (2002), Experimental and Quasi-Experimental Designs for Generalized Causal Inference.  Boston:  Houghton Mifflin. Ch. 4.  “Quasi-Experimental Designs that Either Lack a Control Group or Lack Pretest Observations on the Outcome,”  pp. 103—134

3. Shadish et al, Chapter 5, “Quasi-Experimental Designs that Use both Control Groups and Pretests” pp. 135-170

4. Shadish et al, Ch. 6 “Quasi-Experiments:  Interrupted Time Series Designs” pp. 171-206.

5. Morwitz, Vicki, Eric Johnson, and David Schmittlein (1993), “Does Measuring Intent Change Behavior?” Journal of Consumer Research, 20 (June), 46-61.  Skim lightly, but read the abstract and intro, and be sure you understand what is in Table 1 (p. 50).

Class 8

Date

Topic

Readings

Wed,
Mar. 7

Moderators and Mediators

Reference for later study

Moderated Mediation & Mediated Moderation

1. Baron, Reuben M. and David A. Kenney (1986), "The Moderator-Mediator Variable Distinction in Psychological Research: Conceptual, Strategic, and Statistical Considerations," Journal of Personality and Social Psychology, 51 (6),1173-1182.

2. Irwin, Julie R. and Gary H. McClelland (2001) “Misleading Heuristics and Moderated Multiple Regression Models”  Journal of Marketing Research, 38 (Feb), 100-109.

3. Soman, Dilip (1998), “The Illusion of Delayed Incentives: Evaluating Future Effort-Money Transactions,” Journal of Marketing Research, 35 (November), 427-437.  Read p. 435-436 only. Example discussed in Irwin & McClelland

4. +Shrout, Patrick E. and Niall Bolger (2002), “Mediation in Experimental and Nonexperimental Studies: New Procedures and Recommendations,” Psych Methods, 7(2).

5. Muller, D., Judd, C. M., & Yzerbyt, V. Y. (2005). When mediation is moderated and moderation is mediated. Journal of Personality and Social Psychology, 89(6), 852-863.


Mar. 14 - No Class, Spring Break

Class 9

Date

Topic

Readings

Wed, Mar. 21

Experimental Procedure

 

Distributed but Not Assigned. Discussed in Shepanski et al.

Within v. between subject designs

Manipulation and confounding checks

1. Aronson, Ellsworth, Carlsmith, and Gonzales, Ch. 2, “Some Problems with Experimentation in Social Psychology”  (pp. 40-82)

2. AECG, Ch. 7, “The Independent Variable”, pp. 205-237.

3. + Shimp, Terrence, Eva Hyatt, and David Snyder, (1991) “A Critical Appraisal of Demand Artifacts in Consumer Research, “Journal of Consumer Research, 18 (December), 273-283.

4. Shepanski , A., R. M. Tubbs, and R.A. Grimlund (1992), “Issues of Concern Regarding Within- and Between-Subjects Designs in Behavioral Accounting Research”. Journal of Accounting Literature, 11, 121-150.

5. Perdue, Barbara C. and John O. Summers (1986), “Checking the Success of Manipulations in Marketing Experiments,” Journal of Marketing Research, 23, 317-326.

Class 10

Date

Topic

Readings

Wed,
Mar. 28

Experimental Design

Theory-Testing, Falsification, Strong Inference. 

Debate on Independent v. Dependent Variables Approaches to Theory Testing.

Confounding and what to do about it.

1. Garner, William R., Harold H. Hake and Charles W. Eriksen (1956), “Operationism and the Concept of Perception,” Psychological Review, 63, 149-159.

2. Platt, J.R. (1964), “Strong Inference,” Science, 146, 347-353.

3. +Sternthal, Brian, Alice M. Tybout, and Bobby J. Calder (1987), “Confirmatory versus Comparative Approaches to Judging Theory Tests”  Journal of Consumer Research, , 14 (June), 114-125.  (Optional)

4. Brinberg, David L., John G. Lynch, Jr., and Alan G. Sawyer,(1992) "Hypothesized and Confounded Explanations in Theory Tests: A Bayesian Analysis."  Journal of Consumer Research,  19 (September), 139-154.

Class 11

Date

Topic

Readings

Wed, Apr. 4

 

Overview of the Survey Process; Why Use Surveys?

Sampling, Questionnaire Design

Survey Administration & Data collection

Cognitive Psychology of Responding to Surveys

1. Visser, Penny, John A. Krosnick, and Paul J. Lavrakas, (2000),“Survey Research.” In Harry T. Reis and Charles M Judd (Eds.) Handbook of Research Methods in Personality and Social Psychology.  Cambridge: Cambridge University Press, pp. 223-230.

2. Visser et al, pp. 230-237,  pp. 237-241.

3. Visser et al. pp. 243-247

4. Schwarz, Norbert (1999), “Self Reports: How the Questions Shape the Answers,” American Psychologist, 54 (2), 93–105

Class 12

Date

Topic

Readings

Wed, Apr. 12

Ethics

Institutional Review Board Policies & Forms

1. Aronson, Ellsworth, Carlsmith, and Gonzales, Ch. 3, “Ethical Issues,”  pp. 83-113.

2. APA Code of Ethics  www.apa.org/ethics/code2002.html

3. Lynch, John (1997), “President’s Column: Small Thinking about Ethical Conduct in Consumer Research”, ACR News, September www.acrwebsite.org/newsletter/webnews/pdf/Sept97.pdf

4. Lynch, John (1997) ,“President’s Column:  Closing Thoughts about Ethics and Personal Responsibility,” ACR News, December (pp. 1-6 only) www.acrwebsite.org/newsletter/webnews/pdf/Dec.97.pdf   Read section on “The Plagiarism Trilogy”

5. http://www.ors.duke.edu/irb/index.html

Class 13

Date

Topic

Readings

Wed, Apr. 19

Endings: Writing up Research Reports

 

 

Implications for  Reviewing

1. Bem, Daryl J. (2002), “Writing the Empirical Journal Article,” In Darley, J.M., Zanna, M.P., & Roediger III, H.L. (Eds.), The Compleat Academic:  A Career Guide.  Washington, DC: American Psychological Association. Each person in class should bring in an example of a well-written, engaging article and a contrasting (badly written) one.

2. Abelson, Robert P. (1995), “Chapter 1:  Making Claims with Statistics,” in Statistics as Principled Argument, Hillsdale, NU:  Lawrence Erlbaum Associates, 1-16.   Focus especially on pp. 11-16 and the MAGIC criteria

3. Abelson, Robert P. (1995), “Chapter 8:  Interestingness of an Argument´in Statistics as Principled Argument, Hillsdale, NU:  Lawrence Erlbaum Associates, 156-169.

4. Lynch, John G., Jr.  “Presidential Address: Reviewing.” In Joseph W. Alba and J. Wesley Hutchinson (Eds.) Advances in Consumer Research, Vol. 25.  Provo, Utah:  Association for Consumer Research, 1998, 1-6.