This paper considers an econometric model for new product sales, which extends the deterministic Gompertz process by allowing the saturation level to depend on forcing variables. It turns out that this model can be written in error correction form. Given that many marketing variables show nonstationary behavior, one may have to rely on cointegration techniques for proper estimation of its parameters. Empirical specification strategies are proposed and applied to modeling Dutch new car sales.

Additional Metadata
Keywords cointegration analysis, econometric models
Persistent URL dx.doi.org/10.1016/0167-8116(94)00013-1, hdl.handle.net/1765/2113
Series ERIM Top-Core Articles
Journal International Journal of Research in Marketing
Citation
Franses, Ph.H.B.F. (1994). Modeling new product sales; an application of cointegration analysis. International Journal of Research in Marketing, 491–502. doi:10.1016/0167-8116(94)00013-1