Incentives in Experiments: A Theoretical Analysis

Date: 2016-01
By: Paul J. Healy (Department of Economics, Ohio State University)
Yaron Azrieli (Department of Economics, Ohio State University)
Christopher P. Chambers (Department of Economics, University of California, San Diego)
Experimental economists currently lack a convention for how to pay subjects in experiments with multiple tasks. We provide a theoretical framework for analyzing this question. Assuming monotonicity (dominated gambles are never chosen) and nothing else, we prove that paying for one randomly-chosen problem — the random problem selection (RPS) mechanism — is essentially the only incentive compatible mechanism. Paying for every period is similarly justified when we assume only a ‘no complementarities at the top’ (NCaT) condition. To help experimenters decide which is appropriate for their particular experiment, we also discuss empirical tests of these two assumptions.
Keywords: Experimental design, decision theory, mechanism design
JEL: C90 D01 D81