Implicit institutional incentives and individual decisions: Causal inference with deep learning models

Abstract

Reward schemes guide choices. However, they are not necessarily presented as a collection of written incentive mechanisms but as complex and implicit cues. This paper proposes a methodology to identify tacit organizational incentives based on direct observations of institutional reactions to operational decisions. Football data provides a laboratory for this analysis as referee decisions, and their consequences are subject to public scrutiny. This allows estimating the length of time between referee appointments in Spanish football as a function of referee decisions in the most recent match. A deep learning model is instrumental in this analysis as it allows controlling for many potential confounders. Our results are consistent with the presence of institutional incentives for the referee to take gradual (instead of drastic) decisions to send off home team players and deliver the game's expected outcome. Finally, we discuss the implications of these findings in organizations.