Choosing Response Models for Budget Allocation in Heterogeneous and Dynamic Markets: Why Simple Sometimes Does Better

Abstract

Calibrating a sales response model for budget allocation is a complex task. Since sales response may be different across allocation units and usually involves dynamic relationships, a sufficient number of observations are required for estimation. However, many applications are characterized by small samples, thus raising the question of whether the available data is always rich enough for complex econometric estimation techniques. Otherwise, the researcher may be better off using simpler estimation techniques or just allocation heuristics, even if they are theoretically inferior. We test this proposition by conducting a comprehensive Monte Carlo simulation study using a large number of data conditions ranging from rich to very poor. To evaluate the success of the respective model calibration strategy, we use expected profits resulting from the proposed allocation decision instead of the usual parameter recovery. Using this novel measure, we find that when the data quality is questionable, using simple response models like fixed effects or even allocation heuristics can be very effective from an allocation decision maker's point of view.