Paper: arXiv 2512.23640

Authors: Siqi Shao, Arshia Ghasemi, Hamed Farahani, R. A. Serota

Abstract

We argue that negative skew and positive mean of the distribution of stock returns are largely due to the broken symmetry of stochastic volatility governing gains and losses. Starting with stochastic differential equations for stock returns and for stochastic volatility we argue that the distribution of stock returns can be effectively split in two – for gains and losses – assuming difference in parameters of their respective stochastic volatilities. A modified Jones-Faddy skew t-distribution utilized here allows to reflect this in a single organic distribution which tends to meaningfully capture this asymmetry. We illustrate its application on distribution of daily S&P500 returns, including analysis of its tails.

Complexity vs Empirical Score

  • Math Complexity: 8.0/10
  • Empirical Rigor: 3.0/10
  • Quadrant: Lab Rats — high math complexity, limited empirical testing

Why this score: The paper is mathematically dense, featuring numerous stochastic differential equations, modified Jones-Faddy distributions, and analytical derivations of statistical moments. However, the empirical component is limited to fitting a single distribution (modified Jones-Faddy) to S&P 500 daily returns without any backtesting, performance metrics, or data implementation heavy analysis beyond descriptive fitting.

Research Flowchart

  flowchart TD
  Start(["Research Goal: <br>Model asymmetry in stock returns"]) --> Method["Start with SDEs for<br>stock returns & volatility"]
  Method --> Split["Split distribution into<br>Gains vs Losses based on<br>stochastic volatility parameters"]
  Split --> Mod["Apply Modified<br>Jones-Faddy Skew t-Distribution"]
  Mod --> Compute["Fit distribution to<br>S&P 500 daily returns data"]
  Compute --> Findings["Key Findings:<br>- Captures negative skew<br>- Models asymmetric volatility<br>- Analyzes tail risk"]
  
  style Start fill:#e1f5fe,stroke:#01579b,stroke-width:2px
  style Findings fill:#f1f8e9,stroke:#33691e,stroke-width:2px

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes a modified Jones‑Faddy skew t‑distribution to capture the broken symmetry of stochastic volatility between gains and losses in stock returns.

Source sentence
A modified Jones‑Faddy skew t‑distribution utilized here allows to reflect this in a single organic distribution which tends to meaningfully capture this asymmetry.

Assumes 5

  • The distribution of stock returns can be split into separate gain and loss components with different stochastic volatility parameters. model
    Source sentence
    we argue that the distribution of stock returns can be effectively split in two - for gains and losses - assuming difference in parameters of their respective stochastic volatilities.
  • For the mJF1 specification the mean stochastic volatility is the same for gains and losses (θg = θl = θ). model
    Source sentence
    One possible simplification of this model is to assume that the mean stochastic volatility governing gains and losses is the same, θg = θl = θ
  • Losses have a smaller power‑law exponent (αl) than gains (αg), leading to heavier negative tails. model
    Source sentence
    main culprit for explaining heavier power‑law dependence of losses is assuming that resulting parameter for losses, αl, is smaller than that for gains, αg
  • The location parameter (µ) accounts for the positive mean of the return distribution. model
    Source sentence
    An additional innocuous introduction of the location parameter helps to explain the positive mean of the distribution.
Show 1 more
  • The modified Jones‑Faddy distributions are not derived from first‑principles SDEs but are close in spirit and yield good fits. other
    Source sentence
    modified Jones‑Faddy (mJF) distributions that we use are not cleanly derived from SDE formalism but on the other hand they are close in spirit and yield good fits to the full distribution of returns.

Data

  • S&P500 daily returns · Yahoo! Finance market-prices public
    S&P500 index
    Source sentence
    We obtained S&P500 data at Yahoo! Finance.

Recognised sources: Yahoo Finance

Costs

Not applicable The paper reports no trading or execution result.

Finds 4

  • The modified Jones‑Faddy skew t‑distribution (mJF1) best captures the empirical S&P500 return distribution, including heavier loss tails and positive mean. theoretical
    Source sentence
    Our main conclusion is that a modified Jones‑Faddy skew t‑distribution, (19)-(22) is most likely the best candidate for the stated purpose
  • Introducing a second mean volatility parameter (θg, θl) in mJF2 yields virtually no improvement over mJF1 in fitting the data. statistical
    Source sentence
    extra parameter, showed virtually no difference relative to mJF1 in fitting the empirical data, both visually and based on statistical tests described in Sec. 3.
  • Assuming αl < αg explains the heavier power‑law tails of losses observed in the S&P500 return distribution. theoretical
    Source sentence
    main culprit for explaining heavier power‑law dependence of losses is assuming that resulting parameter for losses, αl, is smaller than that for gains, αg
  • The location parameter accounts for both a larger number of gains than losses and larger gain values in the bulk, offsetting the heavier negative tails. theoretical
    Source sentence
    The location parameter seems to account not only for larger number of gains than losses but also for larger values of gains in the bulk of the distribution which offsets the heavier negative tails.

Checked by others

Supported by

  • Beyond the Bid-Ask: Strategic Insights into Spread Prediction and the Global Mid-Price Phenomenon (2024)
    On the question: Do stock return distributions exhibit heavy‑tailed behavior and how can it be modeled?
    Compare the findings

    This paper: Assuming αl < αg explains the heavier power‑law tails of losses observed in the S&P500 return distribution.

    That paper: Log‑return distributions of both TMOBBAS and GMP exhibit heavy tails and significant deviations from normality.

    Both find heavy tails: A reports heavy‑tailed log‑returns for TMOBBAS and GMP; B explains heavier loss tails in S&P500 via αl<αg. Empirical vs theoretical, different markets.

Cited by 1 paper in the archive

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (21)

  1. Skewness in Stock Returns: Reconciling the Evidence on Firm Versus Aggregate Returns (2012)
  2. Are there Dragon Kings in the Stock Market? — → 2307.03693
  3. Robust statistical tests of Dragon-Kings beyond power law distribution (2012)
  4. Black swans or dragon-kings? A simple test for deviations from the power law (2012)
  5. Inverse Gamma Distribution, https://reference.wolfram.com/language/ref/InverseGammaDistribution.html
  6. Student t Distribution, https://reference.wolfram.com/language/ref/StudentTDistribution.html
  7. NIST Digital Library of Mathematical Functions, https://dlmf.nist.gov/
  8. Probability and Statistical Models with Applications (2001)
and 13 more
  1. A skew extension of the t-distribution, with applications (2003)
  2. A model for stock returns and volatility (2014)
  3. A closed-form solution for options with stochastic volatility with applications to bond and currency options (1993)
  4. Asymmetry in Distributions of Accumulated Gains and Losses in Stock Returns — → 2503.24241
  5. Distributions of Historic Market Data – Stock Returns (2019)
  6. Universal behavior of extreme price movements in stock markets (2009)
  7. Stochastic volatility and leverage effect (2003)
  8. Combined Mutiplicative-Heston Model for Stochastic Volatility (2021)
  9. Distributions of historic market data: relaxation and correlations (2021)
  10. Probability distribution of returns in the Heston model with stochastic volatility (2002)
  11. The distribution of share price changes (1972)
  12. Arch models as diffusion approximations (1990)
  13. A theory of the term structure of interest rates (1985)

2 of 21 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.