Demand for ready-to-eat cereals with household-level censored purchase data and nutrition label information: A distance metric approach

We investigate the demand for ready-to-eat (RTE) breakfast cereals in the United States using censored, household-level purchase data matched with product-level nutrition data. Instead of using a multi-equation based approach, we propose an alternative approach that relies on Pinkse, Slade, and Brett's (2002) distance-metric (DM) method, which is highly practical and less burdensome computationally than some multiple-equation methods. Among other results, we find that households with children are less price sensitive to cereals with whole grain as the first ingredient and to cereals that contain a higher number of fortified vitamins. In addition, we find that households tend to switch between products with similar fiber content and whole grain content profiles.