Beyond Risk: A Measure of Distribution Uncertainty

Uncertainty, particularly distribution uncertainty (a.k.a. ambiguity), holds significant relevance in both academic research and practical applications. Much of the existing research, however, has concentrated primarily on addressing outcome uncertainty (or risk), frequently neglecting the aspect of distribution uncertainty. This research delves into distribution uncertainty, a critical yet often overlooked aspect of empirical research. We argue that there is a pressing need to integrate considerations of ambiguity directly into the development and implementation of data analytics models, calling for the promotion and wider use of a well-defined measure of ambiguity. We introduce a quantitative measure of ambiguity that surpasses conventional approaches by precisely capturing distribution uncertainty. We illustrate the properties and advantages of this measure, highlighting its ability to enhance empirical models, yield more reliable parameter estimates, and contribute to the decision-making process. Using decision making in the financial market as an example, we demonstrate the value of this ambiguity measure. This paper promotes a more nuanced understanding of uncertainty and offers implications for both research methodologies and practical risk management.

History: Yong Tan, Senior Editor; Chad Ho, Associate Editor.

Funding: This work was supported by the University Grants Committee Research Grants Council [Grants GRF 14500521, 165052947, 14501320, 14503818, and TRS:T31-604/18-N], the National Natural Science Foundation of China [Grants 72121001, 72301125], the Tsinghua University Initiative Scientific Research Program [Grant 2021THZWJC28], and the Shenzhen Stable Support Plan Program for Higher Education Institutions [Grant 20220815111555004].

Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2022.0089.