Prerequisite: Advanced Graduate Standing and MKT 5355 Or Consent of Instructor

Course Syllabus

MKT 6355 – Research Methods II

Fall 2001

Instructor: Dr. Dennis B. Arnett

Office: BA 705

Phone: 742-2951

E-mail:

Prerequisite: Advanced graduate standing and MKT 5355 or consent of instructor.

Note: All statements in this syllabus are tentative and, therefore, subject to change. The student is responsible for staying informed of all changes.

Course Description: An in-depth examination of measurement issues, including latent constructs and data-gathering procedures in marketing.

Objectives: The course is designed for students who need a significant familiarity with those statistical analysis techniques known as “structural equation modeling.” The primary objectives of this class are to give students the ability to: (1) recognize the instances when these techniques may be useful in research, (2) ability to understand the limitations of these techniques, and (3) use these techniques in their own research programs.

Grading: The student’s course grade will be calculated as follows:

First Examination20%

Second Examination20%

Class Participation20%

Individual Project40%

Individual Project: Using your own dataset (or one that you begged, borrowed, or stole) develop and test a model. You must use LISREL for your analysis. Once the analysis is complete write up your results (i.e., the methods section of a paper). Use the style of a major journal in your area that normally publishes articles that use SEM techniques.

Suggested Resources:

Books

Bollen, Ken (1989), Structural Equation Modeling with Latent Variables, New York: John Wiley and Sons.

Loehlin, J.C. (1992), Latent Variable Models: An Introduction to Factor, Path, and Structural Analysis (2nd Edition), Hillsdale, NJ: Earlbaum Associates.

Schumacker, Randall E. and Richard G. Lomax (1996), A Beginner’s Guide to Structural Equation Modeling, Mahwah, NJ: Earlbaum Associates.

Websites

David Kenny’s site (

Ed Rigdon’s site (

Wynne Chin’s site (

Student Software

LISREL (Student Edition) (

PLS Path (Version 3.01) (available from me)

Tentative Class Topics

August 28th … Topic 1: Introduction to class

Assigned readings for next class:

Meehl, Paul E. (1990), “Why Summaries of Research on Psychological Theories are often Uninterpretable,” Psychological Reports, 66(1), 367-375.

(Students will be responsible for presenting their understanding of assigned points in the article.)

Hunt, Shelby D. (1991), Modern Marketing Theory, Cincinnati, OH: South-Western Publishing Co., pp. 78-89.

Topic 2: (A) What do we mean when we say that we are testing a theory? (B) Do “good” theories explain, predict, or do both?

Assigned readings for next topic:

LISREL notation cheat sheet (from me)

Chapter 3 in Schumacker, Randall E. and Richard G. Lomax (1996), A Beginner’s Guide to Structural Equation Modeling, Mahwah, NJ: Earlbaum Associates.

Rigdon, Edward E. (1998), “Structural Equation Modeling,” in Modern Methods for Business Research, George A. Marcoulides (ed.), Mahwah, NJ: Earlbaum Associates, pp. 251-294.

Topic 3: (A) Regression? Path Analysis? Exploratory factor analysis? Confirmatory factor analysis? Structural equation modeling? (B) Measurement models versus structural models. (C) Introduction to LISREL notation.

Assigned readings for next topic:

Gerbing, David W. and James C. Anderson (1988), “An Updated Paradigm for Scale Development Incorporating Unidimensionality and Its Assessment,” Journal of Marketing Research, 25(May), 186-192.

Bollen, Kenneth and Richard Kennox (1991), “Conventional Wisdom on Measurement: A Structural Equation Perspective,” Psychological Bulletin, 110(2), 305-314.

Topic 4: Measurement issues. (A) How do we model formative and reflective measures in SEM? (B) Validity. (C) Reliability.

Assigned readings for next topic:

Anderson, James C. and David W. Gerbing (1988), “Structural Equation Modeling in Practice: A Review and Recommended Two-Step Approach,” Psychological Bulletin, 103(3), 411-423.

LISREL sample output (from me)

Topic 5: (A) What is covariance structure analysis? (B) What does it do to my data? (C) What are all those numbers coming out of LISREL? (D) LISREL syntax.

Assigned readings for next topic:

Data (from me)

Topic 6: (A) So, this is a measurement model! (B) Is it a “good” one? (C) Can we make it better?

Assigned readings for next topic:

None. Study for test.

Topic 7: Test! (Tentatively October 9th)

Assigned readings for next topic:

Review Anderson and Gerbing (1988) again.

Topic 8: (A) Convergent validity? (B) Discriminant validity? (C) So, the measurement model fits the data. What next? (B) Predictive validity?

Assigned readings for next topic:

Schumacker, Randall E. and Richard G. Lomax (1996), A Beginner’s Guide to Structural Equation Modeling, Mahwah, NJ: Earlbaum Associates, pp. 119-129

Topic 9: (A) Why are there so many fit indexes? (B) Which one(s) should I use? (C) Can we use other methods of estimation besides ML?

Assigned readings for next topic:

Schumacker, Randall E. and Richard G. Lomax (1996), A Beginner’s Guide to Structural Equation Modeling, Mahwah, NJ: Earlbaum Associates, pp. 25-27.

Chin, Wynne W. and Peter A. Todd (1995), “On the Use, Usefulness, and Ease of Structural Equation Modeling in MIS Research: A Note of Caution,” MIS Quarterly, June, 237-246.

Topic 10: (A) Why isn’t LISREL working? It keeps telling me that the phi matrix is nonpositive definite. (B) How big of a sample should I have? (C) What do you mean it’s not converging? I spent 6 months collecting this data. Now what?

Assigned readings for next topic:

Sellin, Norbert (1995), “Partial Least Squares Modeling in Research on Educational Achievement,” in Reflections on Educational Achievement Papers in Honor of Neville Postlethwaite, Wilfried Bos and Rainer H. Lehmann (eds.), Munich: Waxmann Publishing Co., pp. 256-266.

Sellin, Norbert and J. P Keeves (1998), “Path Analysis and Latent Variables,” in Educational Research, Methodology, and Measurement: An International Handbook, J. P. Keeves (ed), New York: Pergamon Press.

PLSPath output (from me)

Topic 11: (A) PLS, what’s that? (B) Hey, where are the fit indices? (C) Does it fit or not?

Assigned readings for next topic:

Data.

Topic 12: Discuss PLS runs.

Assigned readings for next topic:

Fornell, Claes and Fed L. Bookstein (1982), “Two Structural Equation Models: LISREL and PLS Applied to Consumer Exit-Voice Theory,” Journal of Marketing Research,” 19, 440-452.

Cassel, Claes, Peter Hackl, and Anders H. Westlund (1999), “Robustness of Partial Least-Squares Method for Estimating Latent Variable Quality Structures,” Journal of Applied Statistics, 26(4), 435-446.

Topic 13: When should I use a program, such as LISREL, and when should I use PLS?

Topic 14: Test!! (Tentatively December 4th)

Supplementary Readings

Edwards, Jeffrey R. and Richard P. Bagozzi (2000), “On the Nature and Direction of Relationships Between Constructs and Measures,” Psychological Methods, 5(2), 155-174.

Bollen, Kenneth A. and R. Lennox (1991), “Conventional Wisdom on Measurement: A Structural Equation Perspective,” Psychological Bulletin, 110, 305-314.