Order-constrained inference to supplement experimental data analytics in behavioral economics: A motivational case study

Abstract

A common approach to theory testing in behavioral and experimental economics relies on null hypothesis significance testing via (generalized) linear regression models. Here, we showcase order-constrained inference as an alternative route to theory testing. Order-constrained inference can improve the precision and nuance of behavioral decision analytics. For example, the method can be leveraged to quantify the evidence in support of, or against, a given hypothesis. It also offers advanced model selection tools for quantitative competition among multiple theories. To illustrate our case for order-constrained methods, we re-analyze data from a pre-registered experiment on incentives, cognitive reflection, and dishonest behavior. Building on this publicly available dataset, we further highlight the advantages of Bayesian order-constrained inference. We discuss how the method can deliver more convincing and more nuanced evidence than frequentist null hypothesis significance testing, pointing to new research avenues for supplementing and expanding on experimental designs in behavioral economics.