Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Testing the simplicity of strategy-proof mechanisms

Alexander L. Brown, Daniel G. Stephenson, Rodrigo A. Velez

TL;DR

This study experimentally compares four mechanism designs—DRU, SRU, OSPU, and PFU—for implementing the Uniform allocation rule in a two-agent rationing problem with satiable preferences. PFU, which provides non-binding, real-time feedback during reporting, achieves the highest frequency of Uniform outcomes and overall efficiency, far outperforming DRU, SRU, and OSPU. SRU yields modest improvements by introducing sequential reporting, while OSPU fails to improve performance despite higher node-level dominance cues. The findings highlight the practical value of real-time feedback and sequential structure over purely structurally simpler (OSP) mechanisms and offer nuanced insights into how agents reason and coordinate in these settings. The results have implications for designing allocation rules in settings where satiable preferences and strategic reporting interact, especially in larger, multi-agent contexts where information feedback can be scaled.

Abstract

This paper experimentally evaluates four mechanisms intended to achieve the Uniform outcome in rationing problems (Sprumont, 1991). Our benchmark is the dominant-strategy, direct-revelation mechanism of the Uniform rule. A strategically equivalent mechanism that provides non-binding feedback during the reporting period greatly improves performance. A sequential revelation mechanism produces modest improvements despite not possessing dominant strategies. A novel, obviously strategy-proof mechanism, devised by Arribillaga et al. (2023), does not improve performance. We characterize each alternative to the direct mechanism, finding general lessons about the advantages of real-time feedback and sequentiality of play as well as the potential shortcomings of an obviously strategy-proof mechanism.

Testing the simplicity of strategy-proof mechanisms

TL;DR

This study experimentally compares four mechanism designs—DRU, SRU, OSPU, and PFU—for implementing the Uniform allocation rule in a two-agent rationing problem with satiable preferences. PFU, which provides non-binding, real-time feedback during reporting, achieves the highest frequency of Uniform outcomes and overall efficiency, far outperforming DRU, SRU, and OSPU. SRU yields modest improvements by introducing sequential reporting, while OSPU fails to improve performance despite higher node-level dominance cues. The findings highlight the practical value of real-time feedback and sequential structure over purely structurally simpler (OSP) mechanisms and offer nuanced insights into how agents reason and coordinate in these settings. The results have implications for designing allocation rules in settings where satiable preferences and strategic reporting interact, especially in larger, multi-agent contexts where information feedback can be scaled.

Abstract

This paper experimentally evaluates four mechanisms intended to achieve the Uniform outcome in rationing problems (Sprumont, 1991). Our benchmark is the dominant-strategy, direct-revelation mechanism of the Uniform rule. A strategically equivalent mechanism that provides non-binding feedback during the reporting period greatly improves performance. A sequential revelation mechanism produces modest improvements despite not possessing dominant strategies. A novel, obviously strategy-proof mechanism, devised by Arribillaga et al. (2023), does not improve performance. We characterize each alternative to the direct mechanism, finding general lessons about the advantages of real-time feedback and sequentiality of play as well as the potential shortcomings of an obviously strategy-proof mechanism.
Paper Structure (19 sections, 2 equations, 8 figures, 16 tables)

This paper contains 19 sections, 2 equations, 8 figures, 16 tables.

Table of Contents

  1. Introduction
  2. Uniform Rationing and Mechanisms
  3. Uniform rationing
  4. Uniform rule
  5. Mechanisms
  6. Experimental Design and Procedures
  7. Design
  8. Procedures
  9. Predictions and hypotheses
  10. Equilibrium predictions
  11. Hypotheses
  12. Results
  13. Outcome measures
  14. Individual measures: peak reporting and best response
  15. The success of PFU
  16. ...and 4 more sections

Figures (8)

  • Figure 1: Uniform rule.
  • Figure 2: Direct Revelation Uniform. (DRU)
  • Figure 3: Pre-play Feedback Uniform Rationing. (PFU)
  • Figure 4: Obviously Strategy-proof Uniform Rationing. (OSPU)
  • Figure 5: An example game demonstrating the hierarchy of simplicity concepts involved with an agent identifying a dominant strategy. Suppose Player 1's most (least) preferred outcome is $A$ ($G$) and preferences are such that $C\succsim D, F$. A strategy of choosing "pass" at each node (PPP) is a dominant strategy. PPP is Obviously Dominant if we add $E \succsim F$. Should either $D \succsim F$ or $B \succsim F$ also hold, pass at the initial node is part of a 1-step Simply Dominant path of play. It is part of a 0-step Simply Dominant path of play if both final conditions also hold.
  • ...and 3 more figures