Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.28277

Diversity, Efficiency, and Incentives in Political Prediction Markets

Harry Crane·Koleman Strumpf
View original source ↗Read source document ↗Export metadata ↓

Abstract

Critics of political prediction markets argue that prices are biased because traders are not representative of voters. We test this claim by analyzing data from political betting markets spanning more than 100 years. Our analysis yields two main findings: (1) Acros markets, traders were not representative of the voters. (2) Prices were not biased by political preferences of participants. For the 2024 election, we analyzed anonymized data from Kalshi, a CFTC-regulated exchange, the largest regulated political prediction market in the U.S. Kalshi's traders were 86% male and half were under 30. In its first month of listing election contracts, Kalshi's prices were more accurate than every poll-based forecast in the national race, the seven battleground states, and nineteen Senate races, and no poll-based forecast would have been profitable to trade against them in any group of presidential contests. Its volume came from areas that voted 28% Republican, while 60% of volume went to Republican positions. Traders with a single trade placed 73% of their volume on Harris. The association between a trader's location and the direction of positions declines with trading activity and is zero among active traders, who account for most of the volume. Prices can be accurate with unrepresentative traders when the forecasts of profit-motivated traders do not depend on their demographics. Two other markets corroborate our findings. In New York's 1900 market, bettors were older than the population and drawn from finance. On PredictIt in 2016, which limited each trader to $850 per contract, positions followed registered party more closely, as our theory predicts when market restrictions do not allow profit-motivated traders to set the price. Prediction market efficiency is driven by financial incentives over demographic representativeness.

Explore related subjects

stat.AP

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Harry Crane, Koleman Strumpf. 2026-10-20. Diversity, Efficiency, and Incentives in Political Prediction Markets. https://arxiv.org/abs/2610.28277

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Detecting adverse high-order drug combinations from individual case safety reports using computational statistics on disproportionality measures

Adverse drug reactions linked to the intake of drug combinations are a critical concern in pharmacovigilance, particularly as the controlled environment of clinical trials often lacks the scale and diversity to detect rare events involving multiple medications. While spontaneous reporting systems provide the necessary breadth for post-market surveillance, identifying overrepresented drug cocktails within such large-scale data remains a significant computational challenge. This study introduces a computational framework for the detection of drug cocktails associated with adverse events, leveraging disproportionality analysis on individual case safety reports. By integrating the Anatomical Therapeutic Chemical classification, the framework extends beyond individual drugs to capture hierarchical pharmacological relationships, enabling exploration of the space of drug combinations beyond pairwise analysis. To address biases inherent in existing disproportionality measures, we employ a hypergeometric risk metric, while a Markov Chain Monte Carlo algorithm provides robust empirical p-value estimation for the risk associated with cocktails. A genetic algorithm further facilitates efficient identification of high-risk drug cocktails. A post-treatment step based on penalized logistic regression allows distinguishing true pharmacological interactions from combined individual effects for cocktails of any size. Validation on synthetic and FDA Adverse Event Reporting System data demonstrates the method's efficacy in detecting established drugs and drug combinations associated with myopathy-related adverse events. Implemented as an R package, this framework offers a reproducible, scalable tool for post-market drug safety surveillance.

stat.AP↗
arXiv2026

Can We Trust Evaluations of AI Weather Forecasts for Extremes? How Evaluation Protocols Shape Model Rankings

AI weather models perform competitively with traditional physics-based models at a fraction of the computational cost, and they are thus already used operationally. However, studies reach conflicting conclusions about their ability to forecast extreme weather events, and comparisons across studies are complicated by differing evaluation protocols. We discuss the challenges that arise when comparing AI and physics-based weather forecasts for extreme events. Within a common experimental design, we find that model rankings are highly sensitive to the choice of evaluation metrics: the considered physics-based model tends to perform best when evaluation is restricted to observed extreme events, whereas AI models generally perform better when evaluated using weighted scoring functions. A contingency table analysis shows that AI models underpredict the frequency of extremes, so that their scores are generally dominated by misses, while the physics-based model forecasts extremes more frequently and its scores are dominated by false alarms. Different evaluation metrics penalise these errors differently. Further score decompositions confirm that the score differences arise primarily from miscalibration rather than discrimination ability. This sheds light on the contrasting results in the literature, and highlights the importance of the evaluation metrics used to evaluate AI models.

stat.AP↗
arXiv2026

A Physically-Motivated Stochastic Model of Tropical Cyclone Dynamic Wind Fields

Tropical cyclones (TCs) pose significant risk to infrastructure and human safety, and the frequency and intensity of large TCs are expected to increase in the future. Quantifying such risk to coastal and inland regions is challenging, largely due to the rare nature of TCs which limits historical data availability. We introduce a new stochastic model of TC wind fields conditional on a small number of physical variables commonly found in synthetic and observed storm track databases. The model consists of a physically-motivated mean trend and an expansion of the residual field into a wavelet frame. We demonstrate the approach on a dataset consisting of historical data for storms impacting the northwest Gulf of Mexico. The model adequately captures asymmetry and nonstationary space-time correlation structures of observed wind fields.

stat.AP↗