Layman’s abstract for paper on a Bayesian structural time series model for assessing the effect of advertising expenditures upon sales

Every few days, we will be publishing layman’s abstracts of new articles from our prestigious portfolio of journals in statistics. The aim is to highlight the latest research to a broader audience in an accessible format.

The article featured today is from Applied Stochastic Models in Business and Industry and the full article, published in a recent special issue on Games and Decisions in Risk and Reliability, is available to read online here.

Gallego, V, Suárez‐García, P, Angulo, P, Gómez‐Ullate, D. Assessing the effect of advertising expenditures upon sales: A Bayesian structural time series model. Appl Stochastic Models Bus Ind. 2019; 35: 479– 491. doi: 10.1002/asmb.2460

The goal is to explain the relationship between advertising expenditures of a country-wide fast-food franchise network with its weekly sales, with the intention of helping decision makers choose the advertising budget.

As a basis, the Nerlove–Arrow model is used, which is a classical model for explaining the cumulative effect of advertising upon sales. This model can be interpreted as a Bayesian structural time series model, which is a popular family of models that is both flexible, robust and computationally efficient. This allows us to extend the classical model to our particular problem. Its flexibility and modularity makes it relatively easy to generalize the model to other markets or situations. Its Bayesian nature facilitates incorporating a priori information reflecting the manager’s views, which can be updated with relevant data.

The model can be used to support the decision of the manager on the budget scheduling of the advertising firm across time and channels. Since the model is Bayesian, its output is a probabilistic forecast, which allows the decision maker to take into account both the expected sales and the risk associated to each possible budget allocation.