Paper: arXiv 2410.23587
Authors: Peter Reinhard Hansen, Chen Tong
Abstract
We introduce a novel method for obtaining a wide variety of moments of any random variable with a well-defined moment-generating function (MGF). We derive new expressions for fractional moments and fractional absolute moments, both central and non-central moments. The expressions are relatively simple integrals that involve the MGF, but do not require its derivatives. We label the new method CMGF because it uses a complex extension of the MGF and can be used to obtain complex moments. We illustrate the new method with three applications where the MGF is available in closed-form, while the corresponding densities and the derivatives of the MGF are either unavailable or very difficult to obtain.
Complexity vs Empirical Score
- Math Complexity: 9.0/10
- Empirical Rigor: 2.0/10
- Quadrant: Lab Rats — high math complexity, limited empirical testing
Why this score: The paper presents a novel mathematical framework with advanced complex analysis and integral transforms to derive new expressions for moments, including complex and fractional moments, which is highly mathematically dense. However, the applications are purely theoretical demonstrations (e.g., normal-inverse Gaussian, Heston-Nandi GARCH, HARG) without any code, backtested performance metrics, or implementation details for empirical data, placing it in the Lab Rats quadrant.
Research Flowchart
flowchart TD
A["Research Goal: Develop method for moments without MGF derivatives"] --> B{"Key Methodology"}
B --> C["Extend MGF to Complex Plane"]
C --> D["Derive Integral Expressions<br>for Fractional & Complex Moments"]
E["Data: Closed-form MGFs<br>from 3 Applications"] --> F["Computational Process"]
subgraph F
F1["Apply CMGF Formulas"]
F2["Integrate via<br>Complex Analysis"]
end
F --> G["Key Findings/Outcomes"]
G --> H["Novel CMGF Method<br>Derives moments without derivatives"]
G --> I["New Formulas for<br>Fractional & Absolute Moments"]
G --> J["Validated on 3 Cases<br>where density/derivatives unavailable"]
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 novel method called CMGF that computes a wide variety of integer, fractional, absolute, central, and complex moments of random variables using a complex extension of the moment‑generating function, without requiring derivatives of the MGF.
Source sentence
We introduce a novel method for obtaining a wide variety of moments of any random variable with a well-defined moment-generating function (MGF). We label the new method CMGF because it uses a complex extension of the MGF and can be used to obtain complex moments.
Assumes 3
- The random variable X has one‑sided exponential moments, i.e., E[e^{±sX}] < ∞ for some s > 0. model
Source sentence
Assump-tions on one-sided exponential moments of X (i.e., E[e±sX] < ∞for some s > 0) are stated with each theorem.
- For Re(r) ∈ (−1,0) it is additionally assumed that E[|X−ξ|^{r}] < ∞ to justify exchanging expectation and integration. statistical
Source sentence
When Re(r) ∈(−1, 0), we additionally assume E, |X −ξ|r < ∞to justify exchanging expectation and integration.
- The complex logarithm principal branch is fixed with a cut on (−∞,0] and integrals for −1 < Re(r) ≤ 0 are interpreted as symmetric Cauchy principal values. other
Source sentence
we fix the principal branch of the complex logarithm (branch cut on (−∞, 0]) and interpret integrals as os-cillatory (i.e., symmetric Cauchy principal values) whenever −1 < Re(r) ≤0.
Data
- Daily log‑returns of the S&P 500 index other commercial
Source sentence
The data were obtained from WRDS and the maxi-mum likelihood estimates are presented in Table 2 along with their standard errors (in parentheses). Sample period: January 1, 2000 to December 30, 2021.
- High‑frequency CBOE VIX data for volatility jumps other commercial
Source sentence
We obtain high-frequency VIX data from Tick-data for the sample period from July 1, 2003 to December 30, 2021.
Costs
Not applicable
Finds 3
- The CMGF method is very fast and highly accurate for computing moments of the normal‑inverse Gaussian distribution. theoretical
Source sentence
We found the new method to be very fast and highly accurate for computing mo-ments of the normal-inverse Gaussian distribution.
- The method enables computation of fractional absolute moments of cumulative returns in a Heston‑Nandi GARCH model, fractional moments of realized volatility in an Autoregressive Gamma model, and moments of volatility jumps in an Autoregressive Poisson model. theoretical
Source sentence
Moreover, the CMGF method is especially useful in dynamic models where the MGF is known but derivatives are dif-ficult to obtain, as demonstrated by the three applications in Section 3, where we computed moments of cumulative returns in a Heston-Nandi GARCH model, moments of realized volatilities in a Heterogeneous Autoregressive Gamma model, and moments of number of volatility jumps in an Autoregressive Poisson
- By avoiding MGF derivatives, the CMGF approach simplifies moment calculation in dynamic models where the MGF is known but derivatives are difficult to obtain. theoretical
Source sentence
A key advantage of our approach is that it avoids the need for MGF derivatives, which can be computationally challenging or unavailable in many models. We provided new integral expressions for fractional moments, fractional absolute moments, and central moments that extend the applicability of moment computation that is grounded in the MGF.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 15 related papers). Coverage is partial, so this is neither replication nor refutation.
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 (39)
- The Parabolic Mellin Transform: Gamma and Zeta Integral Representations (2026) — link
- A Unifying Integral Representation of the Gamma Function and Its Reciprocal (2025) — link
- Fractional characteristic functions, and a fractional calculus approach for moments of random variables (2022) — link
- A Jump and Smile Ride: Jump and Variance Risk Premia in Option Pricing* (2019) — link
- Robust benchmarking in noisy environments (2016) — link
- Julia: A Fresh Approach to Numerical Computing (2014) — link
- Smile from the Past: A General Option Pricing Framework with Multiple Volatility and Leverage Components (2014) — link
- Realizing smiles: Options pricing with realized volatility (2013) — link
and 31 more
- Fractional absolute moments of heavy tailed distributions (2013) — link
- Continuous-Time Models, Realized Volatilities, and Testable Distributional Implications for Daily Stock Returns (2010) — link
- Computing VAR and AVaR in Infinitely Divisible Distributions (2009) — link
- Positive-Part Moments via the Fourier–Laplace Transform (2009) — link
- A Simple Approximate Long-Memory Model of Realized Volatility (2008) — link
- Designing Realised Kernels to Measure the Ex-Post Variation of Equity Prices in the Presence of Noise (2008) — link
- Autoregressive Gamma Processes (2006) — link
- Absolute Moments of Generalized Hyperbolic Distributions and Approximate Scaling of Normal Inverse Gaussian Lévy Processes (2005) — link
- From Unit Root to Stein’s Estimator to Fisher’s k Statistics: If You Have a Moment, I Can Tell You More (2005) — link
- A Theory for the Term Structure of Interest Rates (2004) — link
- A Multiple Indicators Model for Volatility Using Intra-Daily Data (2003) — link
- Laplace transforms and suprema of stochastic processes (2002) — link
- Laplace’s Integral, the Gamma Function, and beyond (2002) — link
- A Closed-Form GARCH Option Valuation Model (2000) — link
- Fractional Integrals and Derivatives: Theory and Applications (1993)
- Simulated Moments Estimation of Markov Models of Asset Prices (1993) — link
- A Method of Simulated Moments for Estimation of Discrete Response Models Without Numerical Integration (1989) — link
- Inverse factorial moments (1987) — link
- The Moment-Generating Function and Negative Integer Moments (1981) — link
- Remarks on the relation between fractional moments and fractional derivatives of characteristic functions (1980) — link
- Table Of Integrals Series And Products (2016) — link
- Saddlepoint Approximations for Expectations and an Application to CDO Pricing (2011) — link
- Théorie analytique des probabilités (1995) — link
- Exponential Dispersion Models (1987) — link
- The moment generating function has its moments (1986) — link
- The Fascination of Sand (1985) — link
- An index which distinguishes between some important exponential families (1984)
- Hyperbolic distributions and distributions on hyper-bolae (1978)
- On moments of probability distribution functions (1975) — link
- Fourier analysis in probability theory (1972) — link
- Large Sample Properties of Generalized Method of Moments Estimators
0 of 39 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.