In analyzing panel data, the issue of heterogeneity across households is an important consideration. If heterogeneity is present but is ignored in the analysis, it will result in biased and inconsistent estimates of the effects of marketing mix variables on brand choice. The authors propose the use of a random effects specification to account for heterogeneity in brand preferences across households in a logit framework. The model parameters are estimated by both parametric and semiparametric approaches. The authors also compare their results with those obtained from logit models in which observed past choice behavioir is used to capture such heterogeneity. The different models are estimated with the IRI saltine crackers dataset. A formal statistical test of the model specifications shows that the semiparametric specification is the most preferred in terms of the overall fit of the model to the data. In addition, that specification predicts best when the models are validated in a holdout sample of households.
Get full access to this article
View all access options for this article.
References
1.
AbramowitzMilton, and StegunIrene A. (1972), Handbook of Mathematical Functions.New York: Dover Publications, Inc.
2.
AllenbyGreg (1990), “Hypothesis Testing With Scanner Data: The Advantage of Bayesian Methods,”Journal of Marketing Research, 27(November), 379–89.
3.
AllenbyGreg, and RossiPeter (1990), “Quality Perceptions and Asymmetric Switching Between Brands,” working paper, Ohio State University.
4.
BassFrank M. (1974), “The Theory of Stochastic Preference and Brand Switching,”Journal of Marketing Research, 11(February), 1–20.
5.
BassFrank M., JeulandAbel P., and WrightGordon P. (1976), “Equilibrium Stochastic Choice and Market Penetration Theories: Derivations and Comparisons,”Management Science, 22(June), 1051–63.
6.
Ben-AkivaMoshe, and LermanSteven R. (1985), Discrete Choice Analysis.Cambridge, MA: MIT Press.
7.
BlattbergRobert C., and WisniewskiKenneth J. (1989), “Price-Induced Patterns of Competition,”Marketing Science, 4(Fall), 291–309.
8.
ButlerJ. S., and MoffittR. (1982), “A Computationally Efficient Quadrature Procedure for the One-Factor Multinominal Probit Model,”Econometrica, 50, 761–4.
9.
ChamberlainGary (1980), “Analysis of Covariance With Qualitative Data,”Review of Economic Studies, 47, 225–38.
10.
ColomboRichard, and LandwehrJane (1990), “A Non-Parametric Approach to Incorporating Heterogeneity Into the Logit Model,” working paper, New York University.
11.
CooperLee, and NakanishiMasao (1986), Market Share Analysis.Boston: Kluwer Academic Press.
12.
DalalSiddhartha R., and KleinRoger W. (1988), “A Flexible Class of Discrete Choice Models,”Marketing Science, 7(Summer), 232–51.
13.
GenschDennis H., and ReckerW. W. (1979), “The Multinomial, Multiattribute Logit Choice Model,”Journal of Marketing Research, 16(February), 124–32.
14.
GonulFusun, and SrinivasanKannan (1990), “Modeling Unobserved Heterogeneity in Multinomial Logit Models: Methodological and Managerial Implications,” working paper, Carnegie Mellon University, Pittsburgh.
15.
GuadagniPeter M., and LittleJohn D. C. (1983), “A Logit Model of Brand Choice,”Marketing Science, 2(Summer), 203–38.
16.
GuptaSunil (1988), “Impact of Sales Promotions on When, What, and How Much to Buy,”Journal of Marketing Research, 25(November), 342–55.
17.
HausmanJerry, and HallBronwyn, and GrilichesZvi (1984), “Econometric Models for Count Data With an Application to the Patents-R&D Relationship,”Econometrica, 52, 909–38.
18.
HeckmanJames J. (1981), “The Incidental Parameters Problem and the Problem of Initial Conditions in Estimating a Discrete Time-Discrete Data Stochastic Process,” in Structural Analysis of Discrete Data With Econometric Applications, ManskiC., and McFaddenD., eds. Cambridge, MA: MIT Press.
19.
HeckmanJames J., and SingerBurton (1984), “A Method of Minimizing the Impact of Distributional Assumptions in Econometric Models for Duration Data,”Econometrica, 52(2), 271–320.
20.
HorowitzJoel (1980), “The Accuracy of the Multinomial Logit Model as an Approximation to the Multinomial Probit Model of Travel Demand,”Transportation Research, 14B, 331–41.
21.
HsiaoCheng (1986), Analysis of Panel Data.Cambridge, UK: Cambridge University Press.
22.
JainDipak, and VilcassimNaufel (1991), “Investigating Household Purchase Timing Decisions: A Conditional Hazard Function Approach,”Marketing Science, 10(Spring), 1–15.
23.
JonesJ. Morgan, and LandwehrJane T. (1988), “Removing Heterogeneity Bias From Logit Model Estimation,”Marketing Science, 7(1), 41–59.
24.
KrishnamurthiLakshman, and RajS. P. (1988), “A Model of Brand Choice and Purchase Quantity Price Sensitivities,”Marketing Science, 7(1), 1–20.
25.
KudpiVaman S. (1989), “Incorporating Heterogeneity in Brand Choice Models for Panel Data,” unpublished doctoral dissertation, Northwestern University.
26.
LancasterTony (1979), “Econometric Models for the Duration of Unemployment,”Econometrica, 47(4), 939–56.
27.
McFaddenDaniel (1974), “Conditional Logit Analysis of Qualitative Choice Behavior,” in Frontiers of Econometrics, ZarembkaP., ed. New York: Academic Press, Inc., 105–42.
28.
PressW., and FlemingB., and TenkolskyS., and VetterlingW. (1986), Numerical Receipes.Cambridge, UK: Cambridge University Press.
29.
SrinivasanV., and KibarianThomas (1990), “Purchase Event Feedback: Fact or Fiction?” paper presented at Marketing Science Conference (March 22–25), University of Illinois, Champaign-Urbana.
30.
SteckelJoel H., and VanhonackerWilfred R. (1988), “A Heterogeneous Conditional Logit Model of Choice,”Journal of Business and Economic Statistics, 6(3), 391–8.
31.
VilcassimNaufel J., and JainDipak C. (1991), “Modeling Purchase-Timing and Brand-Switching Behavior Incorporating Explanatory Variables and Unobserved Heterogeneity,”Journal of Marketing Research, 28(February), 29–41.
32.
ZufrydenFred S. (1986), “Multibrand Transition Probabilities as a Function of Explanatory Variables: Estimation by a Least-Squares-Based Approach,”Journal of Marketing Research, 23(May), 177–83.
