Diagnosing competitive reactions using (aggregated) scanner data

Abstract

We study competitive response functions with scanner data on price and promotional activities. Causality tests are used prior to parameter estimation. The results indicate that price and feature have statistically significant causal effects more frequently than other promotional variables and they have disproportionately greater frequencies for quick reactions relative to other instruments. Multiple competitive reactions are common, although the same marketing instrument is more likely to be used to react than a different one. Reactions occur with decreasing probability over time suggesting distinctions between retailer- and manufacturer-dominated reactions. The results can also be used to identify other strategic differences, such as the classification of competitors as leaders and followers.