An Essay on James-Stein Shrinkage and Anchoring
13 Pages Posted: 3 Jan 2018 Last revised: 5 Dec 2018
Date Written: December 1, 2018
Biases may reduce variability, which increases the decision maker's (concave) expected utility. Hence seeking unbiased estimates can be a strictly dominated decision approach under the expected utility criterion. Moreover, James-Stein shrinkage demonstrates that, by aggregating unrelated tasks and leveraging supposedly irrelevant information, the decision maker may actually improve an unbiased decision by "shrinking" it toward an arbitrarily chosen reference point. This revelation points to the difference between probability theory and statistical inference, and it leads to novel testable hypotheses for estimation problems. We reference the behavioral economics literature to illustrate that, compared with models based on probability theory, those based on statistical inference are better at reconciling the difference between normative and descriptive decision theory.
Keywords: Decision Making under Uncertainty, Decision Theory, James-Stein Shrinkage, Anchoring
JEL Classification: B20, C10, C11, D01, D81
Suggested Citation: Suggested Citation