Estimating Micro Relationships from Macro Data: A Comparative Study of two Approximations of the Brand Loyal Model under Temporal Aggregation

Abstract

The data interval bias issue in econometric studies of the relationship between advertising and sales first was discussed in JMR by Clarke in 1976. Within the last few years, several studies reported in the marketing literature have investigated the modeling of sales-advertising relationships with temporally aggregated data. Weiss, Weinberg, and Windal developed an aggregate form of the brand loyal model for data aggregated over time and compared their estimates of micro-level parameters with those derived from an alternative approximation developed by Bass and Leone. The authors use simulated data and empirical data to compare the performance of the two approximation approaches.