Back
Wolfers & Zitzewitz (2004)
webA foundational economics paper on prediction markets, relevant to AI safety discussions around forecasting AI timelines, aggregating expert judgment, and designing mechanisms like Metaculus or prediction market-based governance tools.
Metadata
Importance: 52/100journal articleprimary source
Summary
Wolfers and Zitzewitz provide a foundational survey of prediction markets, examining how these market mechanisms aggregate dispersed information into accurate probabilistic forecasts. They analyze evidence from political, financial, and sports markets, demonstrating that prediction markets often outperform expert opinion and traditional forecasting methods.
Key Points
- •Prediction markets aggregate dispersed private information efficiently through price mechanisms, producing calibrated probabilistic forecasts.
- •Evidence across political elections, sports, and financial markets shows prediction markets consistently outperform polls, expert panels, and other forecasting methods.
- •Market design choices (continuous double auction vs. other formats) affect liquidity and accuracy, with key tradeoffs discussed.
- •Thin markets and manipulation risks are identified as limitations, but empirical evidence suggests these rarely undermine forecast quality.
- •The paper helped establish prediction markets as a credible tool for forecasting policy outcomes and scientific questions.
Review
The paper presents a comprehensive examination of prediction markets as an innovative mechanism for collective forecasting. By analyzing data from multiple contexts, the authors demonstrate that market-generated predictions are typically more accurate than traditional forecasting methods, offering a powerful approach to aggregating dispersed information and generating insights about uncertain events. The study explores the potential of prediction markets across various domains, highlighting their ability to reveal nuanced expectations about probabilities, means, medians, and uncertainty. The authors carefully discuss market design considerations and identify specific contexts where prediction markets are most effective. While acknowledging limitations such as the challenge of distinguishing correlation from causation, they present a compelling case for the value of these markets in understanding complex future scenarios.
Cited by 1 page
| Page | Type | Quality |
|---|---|---|
| Prediction Markets (AI Forecasting) | Approach | 56.0 |
Cached Content Preview
HTTP 200Fetched Apr 9, 20263 KB
Prediction Markets - American Economic Association This website uses cookies. By clicking the "Accept" button or continuing to browse our site, you agree to first-party and session-only cookies being stored on your device to enhance site navigation and analyze site performance and traffic. For more information on our use of cookies, please see our Privacy Policy . Accept Home Journals Journal of Economic Perspectives Spring 2004 Prediction Markets Journal of Economic Perspectives ISSN 0895-3309 (Print) | ISSN 1944-7965 (Online) About the JEP Editors Editorial Policy Annual Report of the Editor Research Highlights Reading Recommendations JEP in the Classroom Contact Information Articles and Issues Current Issue All Issues Information for Authors Guidelines for Proposals Menu About the JEP Editors Editorial Policy Annual Report of the Editor Research Highlights Reading Recommendations JEP in the Classroom Contact Information Articles and Issues Current Issue All Issues Information for Authors Guidelines for Proposals Prediction Markets Justin Wolfers Eric Zitzewitz Journal of Economic Perspectives vol. 18, no. 2, Spring 2004 (pp. 107–126) Download Full Text PDF (Complimentary) Article Information Abstract We analyze the extent to which simple markets can be used to aggregate disperse information into efficient forecasts of uncertain future events. Drawing together data from a range of prediction contexts, we show that market-generated forecasts are typically fairly accurate, and that they outperform most moderately sophisticated benchmarks. Carefully designed contracts can yield insight into the market's expectations about probabilities, means and medians, and also uncertainty about these parameters. Moreover, conditional markets can effectively reveal the market's beliefs about regression coefficients, although we still have the usual problem of disentangling correlation from causation. We discuss a number of market design issues and highlight domains in which prediction markets are most likely to be useful. Citation Wolfers, Justin, and Eric Zitzewitz. 2004. "Prediction Markets." Journal of Economic Perspectives 18 (2): 107–126 . DOI: 10.1257/0895330041371321 Choose Format: BibTeX EndNote Refer/BibIX RIS Tab-Delimited JEL Classification D84 Expectations; Speculations
Resource ID:
d52dcf2e6c08b5b2 | Stable ID: sid_9p0xXFUtd1