Disciplines

Marketing Modeling: Panel Data and Hierarchical Models


Discipline: EAD5974-1

Concentration area: 12139

Number of Credits: 4

Course load:

Theoretical
(Per week)
Practice
(Per week)
Studies
(Per week)
DurationTotal
848360
Goals:
Management scholars and students have increasing access to hierarchical data to study business-related phenomena. Hierarchical data are data measured across multiple nested units of analysis, be it across units that are naturally nested at a given point in time (e.g. customers nested within stores nested within chains), or multiple measurements over time for the same cross-sectional units (e.g. over time performance of retail stores). Getting the full potential of these data may be challenging, and thus require researchers to include in their statistical toolbox methods that may help overcoming those challenges.

Accordingly, this course makes an introduction to hierarchical and panel data models for management scholars and students. The focus will be on statistical methods for (1) the quantification and critical assessment of hypothetical relationships using nested cross-sectional and panel data, (2) including the special cases of dependent variables that are binary (e.g. ‘yes or no’) or multinomial (e.g. ‘a choice between stores A, B, or C’). Participants will learn how to estimate models for hierarchical and panel data structures and practice their newly acquired skills on several data sets that present various modeling challenges.

Justification:

Content:
General program outline (tentative)
- Basic econometrics refresher (regression models, assumptions, violations, prediction, dummy variables, and interactions)
- Hierarchical and panel data structures (examples of hierarchical cross-sectional observations, time measurements of cross-sectional units)
- Models for hierarchical and panel data structures (regression analysis of hierarchical data, fixed effects, random effects, and random coefficients models)
- Binary and multinomial dependent variables and hierarchical models
- Applications with STATA

Tentative detailed program outline (English only)
Day 1
Course objectives, structure, and overview
Econometrics refresher: the linear regression model
PC Lab session: Hands-on applications
Debriefing

Day 2
Models with limited-dependent and qualitative variables
The Logit, Probit, Nested Logit and Conditional Logit models
Analysis and interpretation of the choice model
PC Lab session: Hands-on applications
Debriefing

Day 3
Hierarchical and panel data structures
Panel data models
PC Lab session: Hands-on applications
Debriefing

Day 4
Non-linear panel data models
PC Lab session: Hands-on applications
Debriefing

Day 5
Hierarchical models
Discussion of students’ research questions
PC Lab session: Hands-on applications
Debriefing

Avaliation methods:

Notes:

Bibliography:
Textbooks
Cameron, A.C. & Trivedi, P.K. (2010), Microeconometrics using Stata. Stata Press (Revised edition). [Day 1: Chapters 1-2 (Introduction to Stata), Chapter 3 (Linear regression basics). Day 2: Chapters 14-16. Day 3: Chapters 8-9. Day 4: Chapter 18. Day 5: Chapter 9.5.]
Verbeek, M. (2008), A guide to modern econometrics. John Wiley & Sons, Ltd (3rd edition). [Day 1: Chapters 2-4. Day 2: Chapter 7. Day 3: Chapter 10.1 and 10.2. Day 4: Chapter 10.7.]

Research papers
Franses, P.-H. (2005), “On the Use of Econometric Models for Policy Simulation in Marketing,” Journal of Marketing Research, Vol. 42, No.1, 4-14.

Louviere, J.J. & Hensher, D.A. (1983), “Using Discrete Choice Models with Experimental Data to Forecast Consumer Demand for a Unique Cultural Event,” Journal of Consumer Research, Vol. 10, No. 3, 348-361.

Rockoff, J.E. (2004), “The Impact of Individual Teachers on Student Achievement: Evidence from Panel Data,” American Economic Review, Vol. 94, No. 2, 247-252.

Guadagni, P.M. & Little, J.D.C. (1983), “A Logit Model of Brand choice Calibrated on Scanner Data,” Marketing Science, Vol. 2, No. 3, 203-238.

Guadagni, P. M. & Little J. D. C. (1998), “When and What to Buy: A Nested Logit Model of Coffee Purchase”, Journal of Forecasting, 17(3-4), 303–326.

Peugh, J. L. (2010), ”A practical guide to multilevel modeling”, Journal of School Psychology, 48(1), 85-112.

Leeflang, P.S.H. & Wittink, D.R. (2000), “Building models for marketing decisions: Past, present and future”, International Journal of Research in Marketing, 17, 105-126.