This paper develops a more accurate and robust baseline sales (sales in the absence of price promotion) using Dynamic Linear Models and a Multiple Structural Change Model (DLM/MSCM). We first discuss the value of utilizing aggregated (chain-level) vs. disaggregated (store-level) point-of-sale (POS) data to estimate baseline sales and measure promotional effectiveness. We then discuss the practical advantage of the DLM/MSCM modeling approach using aggregated data, and we propose two tests to determine the superiority of a particular baseline estimate: the minimization of weekly sales volatility and the existence of no correlation with promotional activities in these estimates. Finally, we test this baseline against the industry standard ones on the two measures of performance. Our tests find the DLM/MSCM baseline sales to be superior to the existing log-linear models by reducing the weekly baseline sales volatility by over 80% and by being uncorrelated to promotional activities.
