Abstract
The authors analyze cross-category differences derived from a data source new to the marketing literature. For each of 331 separate grocery product categories, the authors examine two sets of variables, one set consisting of structural characteristics of each category, such as average purchase cycle and household penetration, and the other containing detailed promotional movement information. The overall approach is exploratory. For each set of variables, a separate cluster configuration is derived, which effectively conveys a broad yet meaningful classification of the full set of products. These clusters are then integrated and several hypotheses relating category structure to promotional activity are tested. These relationships have several remarkably strong and consistent patterns across categories. Future directions for cross-category research are discussed.
Get full access to this article
View all access options for this article.