Probability Weighting Meets Heavy Tails: An Econometric Framework for Behavioral Asset Pricing
A new financial model combining heavy-tailed Student-t distributions and behavioral probability weighting offers a more accurate way to assess asset risk. Analyzing 432,000 daily data points from 86 assets, researchers found traditional Gaussian models underestimate extreme risks by nearly 20 percent, while the new method cuts this to 3.2 percent. The model’s behavioral adjustment keeps key mathematical properties for pricing and risk management. However, it mainly covers single assets, leaving multivariate analysis for future work.
What it examines
This paper creates a new econometric model that combines heavy-tailed Student-t distributions with behavioral probability weighting, while keeping key mathematical properties. It aims to improve asset pricing and risk measurement by jointly modeling market tail risks and investor behavior, using large-scale financial data.
What it concludes
The study shows that the new model fits financial data much better than traditional Gaussian models, leading to more accurate risk estimates. This approach can be used for better asset pricing, risk management, and regulatory decisions. Future research may extend it to more complex financial settings and high-frequency data.
Evidence objects
A new financial model blends heavy-tailed Student-t distributions with behavioral probability weighting, sharply improving risk estimates and reducing extreme risk underestimation from nearly 20% to just 3.2% compared to traditional Gaussian models.
key_findings bullet 1 · key_findings · validation V0
Analyzing 432,000 daily observations across 86 assets, researchers found Student-t models outperform Gaussian ones in 88.4% of cases, with behavioral distortions statistically significant for most assets and robust across market conditions, including crises.
key_findings bullet 2 · key_findings · validation V0
The study introduces innovative estimation techniques that jointly identify tail risk and behavioral bias, preserving 'infinite divisibility'crucial for dynamic pricingthough it mainly focuses on univariate models, leaving multivariate and high-frequency settings for future research.
key_findings bullet 3 · key_findings · validation V0
This paper introduces an original econometric framework combining heavy-tailed Student-t distributions and behavioral probability weighting, uniquely preserving infinite divisibility. Its rigorous integration of statistical and behavioral elements is novel, enabling superior risk measurement (e.g., Value-at-Risk) over Gaussian models. The approachs mathematical depth and empirical relevance make it compelling and influential.
key_findings bullet 4 · key_findings · validation V0
Raw abstract and provenance
Abstract: We develop an econometric framework integrating heavy-tailed Student's $t$ distributions with behavioral probability weighting while preserving infinite divisibility. Using 432{,}752 observations across 86 assets (2004--2024), we demonstrate Student's $t$ specifications outperform Gaussian models in 88.4\% of cases. Bounded probability-weighting transformations preserve mathematical properties req… ▽ More We develop an econometric framework integrating heavy-tailed Student's $t$ distributions with behavioral probability weighting while preserving infinite divisibility. Using 432{,}752 observations across 86 assets (2004--2024), we demonstrate Student's $t$ specifications outperform Gaussian models in 88.4\% of cases. Bounded probability-weighting transformations preserve mathematical properties required for dynamic pricing. Gaussian models underestimate 99\% Value-at-Risk by 19.7\% versus 3.2\% for our specification. Joint estimation procedures identify tail and behavioral parameters with established asymptotic properties. Results provide robust inference for asset-pricing applications where heavy tails and behavioral distortions coexist. △ Less
Source row: 1610 · abstract type: unknown