Consumer panel data are typically available for a fixed duration of time (say, a year) during which buyers invariably make different numbers of purchases in the product class. The author describes a method for obtaining maximum likelihood estimates of zero-order models from panel data containing different numbers of purchase records per household. Empirical data are presented to illustrate the application of the estimation method.
Get full access to this article
View all access options for this article.
References
1.
ChatfieldC. and GoodhardtG. J. (1970), “The Beta-Binomial Model for Consumer Purchasing Behavior,” Applied Statistics, 19 (June), 240–50.
2.
EhrenbergA. S. C. (1972), Repeat-Buying. Amsterdam: North-Holland Publishing Company.
3.
KalwaniM. U. and MorrisonDonald G. (1977), “Estimating the Proportion of ‘Always Buy’ and ‘Never Buy’ Consumers: A Likelihood Ratio Test with Sample Size Implications,” Journal of Marketing Research, 14 (November), 601–6.
4.
KalwaniM. U. and MorrisonDonald G. (1980), “Sample Size Requirements for Zero-Order Models,” Journal of Marketing Research, 17 (May), 221–7.
5.
KleinmanJoel C. (1973), “Proportions with Extraneous Variance: Single and Independent Samples,” Journal of the American Statistical Association, 68 (March), 46–54.
6.
MassyW. F., MontgomeryD. B., and MorrisonD. G. (1970), Stochastic Models of Buyer Behavior. Cambridge: MIT Press.
7.
RaoC. R. (1965), Linear Statistical Inference and Its Applications. New York: John Wiley & Sons, Inc.
8.
ShentonL. R. (1950), “Maximum Likelihood and the Efficiency of Fitting by Moments,” Biometrika, 37 (June), 111–16.
9.
WierengaB. (1974), An Investigation of Brand Choice Processes. Rotterdam: University of Rotterdam Press.
