A Hierarchical Bayes Error Correction Model to Explain Dynamic Effects of Price Changes
Published 8/1/2006
Author: Dennis Fok, Csilla Horváth, Richard Paap, and Philip Hans Franses
View this content
Executive Summary
Among the marketing-mix variables, price and price promotions have the greatest impact on short-term consumer purchase behavior. Thus, price promotions are frequently used in marketing. Systematic relationships between market characteristics and the magnitude of price elasticities have been the focus of many studies. However, because of dynamics in consumers’ response behavior, the cumulative effect of a price promotion may differ from the immediate effect. Because the profitability of a promotion largely depends on these long-term effects, providing insights into the determinants of the cumulative effect is of interest to both brand managers and retailers.
Understanding which factors influence the immediate and long-term effects of changes in regular price is also important for retailers’ and brand managers’ strategic decisions. In this article, the authors analyze which brand- and category-specific characteristics influence the short-term and the long-term effects of price promotions and changes in regular price.
The Bayesian estimation results show that the immediate elasticity and the cumulative elasticity of a price discount in the data set under scrutiny are significantly lower than zero. However, part of the relatively large immediate effect of a price cut disappears over the dust-settling period, probably due to consumers’ stockpiling and purchase acceleration. Across brands, the dispersion of the posterior mean of the immediate effect of a price promotion is larger than the dispersion in the posterior mean of the cumulative effect. This suggests that brands with a relatively large (small) immediate elasticity tend to have a larger (smaller) postpromotion dip. In general, moderating factors that are found to influence the immediate elasticity of price promotions also influence the cumulative elasticity.
The authors find many significant moderating effects for the elasticity of price promotions. Brands in categories that are characterized by high price differentiation and that constitute a lower share of budget are less sensitive to price discounts. Deep price discounts increase the immediate price sensitivity of customers. The authors also find significant effects for the cumulative elasticity. The immediate effect of a regular price change is often close to zero. The long-term effect of a regular price decrease usually amounts to an increase in sales. This is especially true in categories characterized by large price dispersion and frequent price promotions and for hedonic, nonperishable products.
Biography
Dennis Fok is an assistant professor in the Econometric Institute at Erasmus University Rotterdam. His research interests include modeling unobserved heterogeneity, panel models, marketing econometrics, and nonlinear models.
Csilla Horváth is a researcher in the Economics Department at the National Bank of Hungary and in the Statistics Department at Corvinus University of Budapest. Her main contribution to this article took place during her postdoctoral period in the Econometric Institute at Erasmus University of Rotterdam. Her research interests include measuring dynamic effects of promotions, measuring competition and feedback effects, panel data, and time series analysis.
Richard Paap is Associate Professor in Econometrics in the Econometric Institute at Erasmus University Rotterdam. His main research interests are estimating dynamic effects of promotions on sales and market shares, modeling purchase decisions of households, Bayesian econometrics, and time-series analysis.
Philip Hans Franses is Professor of Applied Econometrics and Professor of Marketing Research, both at Erasmus University Rotterdam. Currently, he is the director of the Econometric Institute. His research interests include time-series models and forecasting.
J Marketing Research, Volume 43, Number 3, August 2006
View Table of Contents.