Skip to main content
SpringerLink
Log in

A nested logit model of strategic promotion

  • Published:
Quantitative Marketing and Economics Aims and scope Submit manuscript

Abstract

This paper presents a test of the nature of the pricing and promotion game played by supermarket retailers in a large, U.S. market. Using a nested-logit modeling approach, the results show that retailers set discount depth and promotional frequency in a manner that is less competitive than Bertrand. We also find that the elasticity of substitution among competing stores is lower than among products within each store, but not equal to zero. Therefore, sales do cannibalize existing products, but can also build a significant amount of store-traffic. Relative to strategic factors, price promotions have their greatest impact on store-conditional product demand.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Notes

  1. Zhou (2001) offers another dynamic explanation for sales that regards regular price reductions as necessary to restore brand loyalty given its tendency to degrade slowly over time.

  2. Pauwels et al. (2002) outline a number of other ways in which promotion increases demand independent of the price effect. Impulse buying, stockpiling, purchase acceleration, learning and reinforcement are all ways in which promotions can increase demand independent of the pure price effect. In this study, we focus on the static effects of price promotion on product demand and firm rivalry in both promotional depth and breadth. Although price promotion has dynamic effects (Erdem et al., 2003) for most consumer products, because fresh produce is highly perishable, consumers are not likely to stockpile or accelerate purchases. Moreover, incorporating dynamic rivalry in a theoretically consistent way is beyond the scope of this paper. Pakes and McGuire (1994) provide a theoretical framework for specifying and estimating dynamic models for differentiated product oligopolies.

  3. A reviewer questions our choice of a nested logit model on the argument that consumers buy many different types of fruit on each shopping occasion. However, based on our analysis of a 2,718 household sample of AC Nielsen HomeScan panel data, households tend to buy a single product (UPC coded fruit) 71.9% of the time and one or two products 95.5% of the time. While this does not suggest that purchases are strictly discrete, fresh fruit is a nearer approximation at the household level than the beer data described by Slade (2004) yogurt data in Draganska and Jain (2005), both of which are estimated with discrete choice models. Villas Boas and Zhao (2005) discuss the bias that results when multiple purchases do, in fact, occur within a nested logit framework (p. 86).

  4. Aggregating promotion decisions in this way also represents an alternative approach to estimating discrete games (Bresnahan and Reiss, 1991). Estimating separate equations for each binary discount variable would not only be intractable for reasons of dimensionality, but would require a large-scale simultaneous probit model. Sequential methods could potentially be used to estimate such a system, but as Bresnahan and Reiss (1991) point out, consistent estimates of retailer conduct could not be recovered by imposing cross-equation parameter restrictions implied by the general Nash solution. McAfee (1995) also looks at multi-product retailer price dispersion this way—each retailer chooses a probability of sale rather than a particular product to promote each week.

  5. Note that the solution for ∇ n makes use of the fact that n j =E[d ij ] so the derivative of mean utility in the number of sale products is: \( \partial {\delta_j}/\partial{n_j} = \partial {\delta_j}/\partial{E(d(_{ij})=\alpha_1 + \alpha_2 p_{ij}}\).

  6. The random utility model includes three promotion-related effects: (1) an increase in utility from paying a lower price, as measured by the price elasticity, (2) a shift in demand from the “announcement effect” of a promotion, and (3) a rotation of the demand curve, estimated through an interaction term between the sale indicator and price variables. All three are implicitly assumed to be endogenous in the instrumental variables estimation technique described below.

  7. While the cross-price elasticities also consist of product, store and category components, we simplify the response-estimation procedure by using the partial cross-elasticity. Little additional information is gained by estimating responses to each cross-elasticity component.

  8. We define the GMM weighting matrix as White's (1980) consistent heteroskedastic matrix wherein the weights are variances calculated from a first-stage instrumental-variable regression.

  9. Theil's U statistic is calculated as: \({ U = \sqrt{\frac{(1/n)\sum_i(y_i-\hat{y}_i)^2}{(1/n)\sum_i y^2_i}} }\), where y i is the variable of interest and n is the number of observations in the validation data set.

  10. In the marketing literature, researchers have documented many other possible effects of price promotion. While the store-level scanner data used here is not conducive to estimating the direct effect of promotions on cross-category purchases (Ainslie and Rossi, 1998) or the cherry picking behavior documented by Fox and Hoch (2005), the nested logit model accounts for this type of behavior in an indirect way. Although the IAA property means that price changes for a particular product induce equal-proportionate responses among all other products in the same store, the nested logit scaling parameter picks up the effect of extremely price-sensitive consumers (cherry pickers) going from store to store to find the lowest price for specific products. Without household level data, however, we cannot comment on how individual behavior differs based on the opportunity to take advantage of a price promotion.

  11. Note, of course, that the cross-price elasticities with respect to all other products in the same store are identical. This is a consequence of the IIA property of the nested logit model discussed above. To the extent that these elasticities are driven by market share and not by behavioral responses, these elasticities are somewhat less interesting as estimation “results” than elasticities estimated with models that do not have the IIA property.

  12. Finding a high cross-price elasticity is not inconsistent with our assumption that produce managers set prices on a category-wide basis. In fact, we expect to find wide disparities in own- and cross-price elasticities for products that are not priced optimally on an individual basis. For example, given our empirical results, produce managers should reduce banana prices significantly in order to both raise banana revenue and attract shoppers from other stores. Doing so, however, would lower the estimated demand elasticity until it is approximately equal to that of the other products.

References

  • Ainslie, A., & Rossi, P. E. (1998). Similarities in choice behavior across product categories. Marketing Science, 17, 91–106.

    Google Scholar 

  • Anderson, S. P., & de Palma, A. (1992). Multiproduct firms: a nested logit approach. Journal of Industrial Economics, 40, 261–275.

    Google Scholar 

  • Baker, J. B., & Bresnahan, T. F. (1985). The gains from merger or collusion in product-differentiated industries. Journal of Industrial Economics, 33, 427–444.

    Google Scholar 

  • Berry, S. T. (1994). Estimating discrete choice models of product differentiation. RAND Journal of Economics, 25, 242–262.

    Google Scholar 

  • Besanko, D., Gupta, S., & Jain, D. (1998). Logit demand estimation under competitive pricing behavior: an equilibrium framework. Management Science, 44, 1533–1547.

    Google Scholar 

  • Blinder, A., Canetti, E. Lebow, D., & Rudd, J. (1998). Asking about prices: a new approach to understanding price stickiness. New York, NY: Russell Sage Foundation.

  • Bliss, C. (1988). A theory of retail pricing. Journal of Industrial Economics, 36, 375–390.

    Google Scholar 

  • Bresnahan, T. F., & Reiss, P. C. (1991). Empirical models of discrete games. Journal of Econometrics, 48, 57–81.

    Google Scholar 

  • Cardell, N. S. (1997). Variance components structures for the extreme value and logistic distributions with applications to models of heterogeneity. Econometric Theory, 13, 185–213.

    Google Scholar 

  • Chevalier, J., Kashyap, A., & Rossi, P. (2000). Why don't prices rise during periods of peak demand? Evidence from scanner data. NBER Working Paper 7981. Cambridge, MA, October.

  • Chintagunta, P. K. (2002). Investigating category pricing behavior at a retail chain. Journal of Marketing Research, 39,141–154.

    Google Scholar 

  • Currie, G. R., & Park. S. (2002). The effects of advertising and consumption experience on the demand for antidepressant drugs. Working paper. Department of Economics, University of Calgary, Calgary, Alberta, Canada. March.

  • Dhar, T., & Cotterill, R. W. (2003). Oligopoly pricing with differentiated products: the boston fluid milk market channel. Paper presented at AAEA annual meeting, Montreal, Canada. August.

  • Draganska, M., & Jain, D. (2005). Product-line length as a competitive tool. Journal of Economics and Management Strategy, 14, 1–28.

    Google Scholar 

  • Dube, J.-P. (2004). Multiple discreteness and the demand for carbonated soft drinks. Management Science, 23, 66–81.

    Google Scholar 

  • Dube, J.-P. (2005). Product differentiation and mergers in the carbonated soft drink industry. Journal of Economics and Management Strategy, 14(4), 879–904.

    Google Scholar 

  • Epstein, G. S. (1998). Retail pricing and clearance sales: the multiple product case. Journal of Economics and Business, 50, 551–563.

    Google Scholar 

  • Erdem, T., Imai, S., & Keane, M. P. (2003). A model of consumer brand and quantity choice dynamics under price uncertainty. Quantitative Marketing and Economics, 1, 5–64.

    Google Scholar 

  • Fox, E. J., & Hoch, S. J. (2005). Cherry-picking. Journal of Marketing, 69, 46–62.

    Google Scholar 

  • Gallant, A. R., & Jorgenson, D. W. (1979). Statistical inference for a system of simultaneous, nonlinear, implicit equations in the context of instrumental variable estimation. Journal of Econometrics, 11, 275–302.

    Google Scholar 

  • Gasmi, F., Laffont, J. J., & Vuong, Q. H. (1992). An econometric analysis of collusive behavior in a soft-drink market. Journal of Economics and Management Strategy, 1, 277–311.

    Google Scholar 

  • Genesove, D., & Mullin, W. (1998). Testing static oligopoly models: conduct and cost in the sugar industry, 1890–1914. Rand Journal of Economics, 29, 355–377.

    Google Scholar 

  • Giulietti, M., & Waterson, M. (1997). Multiproduct firms' pricing behaviour in the italian grocery trade. Review of Industrial Organization, 12, 817–832.

    Google Scholar 

  • Greene, W. (2000). Econometric analysis, 3rd edn. Upper Saddle River: Prentice-Hall.

  • Gupta, S. (1988). Impact of sales promotions on when, what, and how much to buy. Journal of Marketing Research, 25, 342–355.

    Google Scholar 

  • Hansen, L. P. (1982). Large sample properties of generalized methods of moments estimators. Econometrica, 50, 1029–1054.

    Google Scholar 

  • Hendel, I., & Nevo, A. (2002). Measuring the implications of sales and consumer stockpiling behavior. Paper presented at Estimation of Dynamic Demand Models seminar. Yale University, November.

  • Hess, J. D., & Gerstner, E. (1987). Loss leader pricing and rain check policy. Marketing Science, 6, 358–374.

    Google Scholar 

  • Hosken, D., & Reiffen, D. (2001). Multiproduct retailers and the sale phenomenon. Agribusiness: An International Journal, 17, 115-137.

    Google Scholar 

  • Hosken, D., & Reiffen, D. (2004). Patterns of retail price variation. RAND Journal of Economics, 35, 128–146.

    Google Scholar 

  • Hosken, D., & Simpson, J. D. (2001). Have supermarket mergers raised prices? An event study analysis. International Journal of the Economics of Business, 8, 329–342.

    Google Scholar 

  • Kadiyali, V., Chintagunta, P., & Vilcassim, N. (1999). Product line extensions and competitive market interactions: an empirical analysis. Journal of Econometrics, 89, 339–363.

    Google Scholar 

  • Lach, S., & Tsiddon, D. (1996). Staggering and synchronization in price-setting: evidence from multiproduct firms. American Economic Review, 86, 1175–1196.

    Google Scholar 

  • Lal, R., & Matutes, C. (1994). Retail pricing and advertising strategies. Journal of Business, 67, 345–370.

    Google Scholar 

  • Levy, D., Bergen, M., & Dutta, S., & Venable, R. (1997). The magnitude of menu costs: direct evidence from large U.S. supermarket chains. Quarterly Journal of Economics, 112, 791–825.

    Google Scholar 

  • MacDonald, J. (2000). Demand, information, and competition: why do food prices fall at seasonal demand peaks? Journal of Industrial Economics, 48, 27–45.

    Google Scholar 

  • McAfee, R. (1995). Multiproduct equilibrium price dispersion. Journal of Economic Theory, 67, 83–105.

    Google Scholar 

  • McFadden, D. (1974). The measurement of urban travel demand. Journal of Public Economics, 3, 303–328.

    Google Scholar 

  • McLaughlin, E. W., Park, K., Perosio, D. J., & Green, G. M. (1999). FreshTracks 1999: the new dynamics of produce buying and selling. Department of Agricultural, Resource, and Managerial Economics, Cornell University.

  • Narasimhan, C. (1988). Competitive promotional strategies. Journal of Business, 61, 427–449.

    Google Scholar 

  • Neslin, S. A., Henderson C., & Quelch, J. (1985). Consumer promotions and the acceleration of product purchases. Marketing Science, 4, 147–165.

    Google Scholar 

  • Nevo, A. (2001). Measuring market power in the ready-to-eat cereal industry. Econometrica, 69, 307–342.

    Google Scholar 

  • Nijs, V. R., Dekimpe, M. G., Steenkamp J.-B. E. M., & Hanssens, D. M. (2001). The category demand effects of price promotions. Marketing Science, 20, 1–22.

    Google Scholar 

  • Pakes, A., & McGuire, P. (1994). Computing markov-perfect nash equilibria: numerical implications of a dynamic differentiated product model. Rand Journal of Economics, 25, 555–589.

    Google Scholar 

  • Pauwels, K., Hanssens, D. M., & Siddarth, S. (2002). The long-term effects of price promotions on category incidence, brand choice and purchase quantity. Journal of Marketing Research, 39, 421–439.

    Google Scholar 

  • Pesendorfer, M. (2002). Retail sales: a study of pricing behavior in supermarkets. Journal of Business, 75, 33–66.

    Google Scholar 

  • Pick, D.H., Karrenbrock, J., & Carman, H.F. (1990). Price asymmetry and marketing margin behavior: an example for california-arizona citrus. Agribusiness: An International Journal, 6, 75–84.

    Google Scholar 

  • Powers, N. J. (1995). Sticky short-run prices and vertical pricing: evidence from the market for iceberg lettuce. Agribusiness: An International Journal, 11, 57–75.

    Google Scholar 

  • Slade, M. E. (1995). Product rivalry with multiple strategic weapons: an analysis of price and advertising competition. Journal of Economics and Management Strategy, 4, 445–476.

    Google Scholar 

  • Sudhir, K. (2001). Structural analysis of manufacturer pricing in the presence of a strategic retailer. Marketing Science, 20, 244–264.

    Google Scholar 

  • Theil, H. (1961). Economic Forecasts and Policy. Amsterdam: North Holland.

  • United States Department of Agriculture. National agricultural statistics service. Market News Service Washington, D.C. various issues.

  • United States Department of Labor. Bureau of labor statistics. Employment, hours, and earnings from the current employment statistics survey. Washington, DC, various issues.

  • Varian, H. (1980). A model of sales. American Economic Review, 70, 651–659.

    Google Scholar 

  • Villas-Boas, J. M. (1995). Models of competitive price promotions: some empirical evidence from the coffee and saltine crackers markets. Journal of Economics and Management Strategy, 4, 85–107.

    Google Scholar 

  • Villas-Boas, J. M., & Winer, R. S. (1999). Endogeneity in brand choice models. Management Science, 445, 1324–1338.

    Google Scholar 

  • Villas-Boas, J. M., & Zhao, Y. (2005). The ketchup marketplace: retailers, manufacturers, and individual consumers. Journal of Marketing Research, 42, 83–95.

    Google Scholar 

  • Villas-Boas, S. (2003). Vertical contracts between manufacturers and retailers: an empirical analysis. Working paper, Department of Agricultural and Resource Economics, University of California at Berkeley, May.

  • Ward, R. W. (1982). Asymmetry in retail, wholesale, and shipping point pricing for fresh vegetables. American Journal of Agricultural Economics, 64, 205–212.

    Google Scholar 

  • Warner, E., & Barsky, R. (1995). The timing and magnitude of retail store markdowns: evidence from weekends and holidays. Quarterly Journal of Economics, 101, 321–352.

    Google Scholar 

  • Werden, J. (1998). Demand elasticities in antitrust analysis. Antitrust Law Journal, 66, 363–414.

    Google Scholar 

  • White, H. (1980). A heteroskedasticity-consistent covariance matrix estimator and a direct test for heteroskedasticity. Econometrica, 48, 817–838.

    Google Scholar 

  • Zhou, W. (2001). Periodic price reduction as a way to boost diminishing demand. Working paper, Department of Economics, Hong Kong University of Science and Technology, Clear Water Bay,Hong Kong.

Download references

Acknowledgments

The author gratefully acknowledge the financial support of the National Institute for Commodity Promotion Research and Evaluation at Cornell University and the Food Systems Research Group and at the University of Wisconsin at Madison.

Author information

Authors and Affiliations

  1. Morrison School of Agribusiness, Arizona State University, 7001 E. Williams Field Rd. Bldg. 20, Mesa, AZ, 85212, USA

    Timothy J. Richards

Authors
  1. Timothy J. Richards
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Timothy J. Richards.

Additional information

JEL classifications L13 · L66 · L81 · M31 · C35

Rights and permissions

Reprints and permissions

About this article

Cite this article

Richards, T.J. A nested logit model of strategic promotion. Quant Market Econ 5, 63–91 (2007). https://doi.org/10.1007/s11129-006-9013-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11129-006-9013-1

Keywords

Search

Navigation