Estimating Cannibalization Rates for Pioneering Innovations

Van Heerde, Harald J.; Srinivasan, Shuba; Dekimpe, Marnik G.
November 2010
Marketing Science;Nov/Dec2010, Vol. 29 Issue 6, p1024
Academic Journal
To evaluate the success of a new product, managers need to determine how much of its new demand is due to cannibalizing the firm's other products, rather than drawing from competition or generating primary demand. We introduce a time-varying vector error-correction model to decompose the base sales of a new product into its constituent sources. The model allows managers to estimate cannibalization effects and calculate the new product's net demand, which may be considerably less than its total demand. We apply our methodology to the introduction of the Lexus RX300 using detailed car transaction data. This case is especially interesting because the Lexus RX300 was the first crossover sport utility vehicle (SUV), implying that its demand could come from both the luxury SUV and the luxury sedan categories. Because Lexus was active in both categories, there was a double cannibalization potential. We show how the contribution of the different demand sources varies over time and discuss the managerial implications for both the focal brand and its competitors.


Related Articles

  • Linear approximations to the quadratic almost ideal demand system. Matsuda, Toshinobu // Empirical Economics;Aug2006, Vol. 31 Issue 3, p663 

    This paper investigates linear approximations to the recently popular quadratic almost ideal demand system (QUAIDS) by proposing a new composite variable and conducting a simulation study. The linear approximations are especially useful when one uses nonstationary time series, to which nonlinear...

  • Predicts Based on Multi Modality Support Vector of the Settlement of Composite Foundation. ZHANG Lihua; LIU Haibo; AN Fengping // Advanced Materials Research;2014, Issue 919-921, p716 

    Composite foundation settlement is affected by many factors, and settlement data is a non-linear changing process with complexity, suddenness and progressive nature and so on. So we must analyze and predict the stability of the foundation settlement. Because empirical mode decomposition...

  • Dynamic Analysis for Geographical Profiling of Serial Cases Based on Bayesian-Time Series. Guanli Huang; Guanhua Huang // Journal of Software (1796217X);Jun2012, Vol. 7 Issue 6, p1242 

    The analysis of spatial information has long been considered valuable for police agency within the criminal investigative process. This is especially true for serial crime cases where criminologists and psychologist apply geographical profiling to model criminal mobility distribution and...

  • Do Bayesians Learn Their Way Out of Ambiguity? Zimper, Alexander // Decision Analysis;Dec2011, Vol. 8 Issue 4, p269 

    In standard models of Bayesian learning, agents reduce their uncertainty about an event's true probability because their consistent estimator concentrates almost surely around this probability's true value as the number of observations becomes large. This paper takes the empirically observed...

  • Identifying Unmet Demand. Chandukala, Sandeep R.; Edwards, Yancy D.; Allenby, Greg M. // Marketing Science;Jan/Feb2011, Vol. 30 Issue 1, p61 

    Brand preferences and marketplace demand are a reflection of the importance of underlying needs of consumers and the efficacy of product attributes for delivering value. Dog owners, for example, may look to dog foods to provide specific benefits for their pets (e.g., shiny coats) that may not be...

  • Time series decomposition. WEST, MIKE // Biometrika;1997, Vol. 84 Issue 2, p489 

    A constructive result on time series decomposition is presented and illustrated. Developed through dynamic linear models, the decomposition is useful in analysis of an observed time series through inference about underlying, latent component series that may have physical interpretations....

  • Markov chain Monte Carlo for dynamic generalised linear models. GAMERMAN, DANI // Biometrika;1998, Vol. 85 Issue 1, p215 

    This paper presents a new methodological approach for carrying out Bayesian inference about dynamic models for exponential family observations. The approach is simulationbased and involves the use of Markov chain Monte Carlo techniques. A Metropolis- Hastings algorithm is combined with the Gibbs...

  • The importance of observation versus process error in analyses of global ungulate populations. Ahrestani, Farshid S.; Hebblewhite, Mark; Post, Eric // Scientific Reports;11/8/2013, p1 

    Population abundance data vary widely in quality and are rarely accurate. The two main components of error in such data are observation and process error. We used Bayesian state space models to estimate the observation and process error in time-series of 55 globally distributed populations of...

  • Seasonal Time Series Data Forecasting by Using Neural Networks Multiscale Autoregressive Model. Suhartono; Ulama, B. S. S.; Endharta, A. J. // American Journal of Applied Sciences;2010, Vol. 7 Issue 10, p1372 

    Problem statement: The aim of this research was to study further some latest progress of wavelet transform for time series forecasting, particularly about Neural Networks Multiscale Autoregressive (NN-MAR). Approach: There were three main issues that be considered further in this research. The...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics