Outlier robust analysis of long-run marketing effects for weekly scanning data

We consider econometric modeling of weekly observed scanning data on a fast moving consumer good (FMCG), with a specific focus on the relationship between market share, distribution, advertising, price, and promotion. Such data can show non-stationary characteristics. Therefore, we use cointegration techniques to quantify the long-run effects of marketing efforts. Since weekly scanning data can contain aberrant observations due to, e.g., out-of-stock situations or measurement errors, we favor an outlier robust cointegration method, which we outline in detail. In our illustrative FMCG example, we find different results across robust and non-robust methods for the long-run marketing effects.