Metrics unreliability and marketing overspending Academic Article uri icon

abstract

  • © 2017 Elsevier B.V. The adverse consequences of measurement unreliability on statistical issues (e.g., inconsistency, attenuation bias) are well known. Yet there exists sparse literature, if any, on how unreliable metrics affect strategic marketing decisions: optimal marketing budget, its optimal allocation to advertising and promotions, and overspending. Consequently, researchers and managers do not know: How to estimate dynamic demand models using unreliable data? How to optimally combine multiple noisy and biased metrics? How to optimally set the total marketing budget and optimally allocate it to advertising and promotions activities using unreliable sales metrics? To answer these open questions, first, based on Kalman filtering theory, we show how to estimate and infer dynamic demand models using unreliable sales metrics. Then, we furnish evidence of significant measurement noise in both retail audit and company's internal data to track brand sales. We replicate these results across six largest political regions in the emerging Indian markets for a major hair care brand. Next, we analytically derive the optimal weights to combine noisy and biased metrics to infer the latent demand. This result uncovers a counter-intuitive insight that two independent noisy metrics are better than one even when the second metric is noisier. In other words, a composite metric serves as noise reduction device as it is more reliable than individual noisy metrics. Subsequently, we derive closed-form expressions for the optimal budget and its optimal allocation to advertising and promotions activities in the presence of unreliable sales metrics. Based on these results, we discover that marketing overspending increase as metrics unreliability increases. Furthermore, overconfidence —the presumption that the metrics are reliable— leads to overspending on advertising and promotions. Managers should reduce advertising and promotional spending when sales metrics are noisy. Finally, we provide a simple correction factor that managers can use to eliminate overspending.

author list (cited authors)

  • Sridhar, S., Naik, P. A., & Kelkar, A.

citation count

  • 3

publication date

  • December 2017