Paper: arXiv 2507.10041

Authors: Sourojyoti Barick

Abstract

This paper provides insight into the estimation and asymptotic behavior of parameters in interest rate models, focusing primarily on the Cox-Ingersoll-Ross (CIR) process and its extension – the more general Chan-Karolyi-Longstaff-Sanders (CKLS) framework (\(α\in[“0.5,1”]\)). The CIR process is widely used in modeling interest rates which possess the mean reverting feature. An Extension of CIR model, CKLS model serves as a foundational case for analyzing more complex dynamics. We employ Euler-Maruyama discretization to transform the continuous-time stochastic differential equations (SDEs) of these models into a discretized form that facilitates efficient simulation and estimation of parameters using linear regression techniques. We established the strong consistency and asymptotic normality of the estimators for the drift and volatility parameters, providing a theoretical underpinning for the parameter estimation process. Additionally, we explore the boundary behavior of these models, particularly in the context of unattainability at zero and infinity, by examining the scale and speed density functions associated with generalized SDEs involving polynomial drift and diffusion terms. Furthermore, we derive sufficient conditions for the existence of a stationary distribution within the CKLS framework and the corresponding stationary density function; and discuss its dependence on model parameters for \(α\in[“0.5,1”]\).

Complexity vs Empirical Score

  • Math Complexity: 8.5/10
  • Empirical Rigor: 3.5/10
  • Quadrant: Lab Rats — high math complexity, limited empirical testing

Why this score: The paper employs advanced stochastic calculus, SDE analysis, and asymptotic proofs, resulting in high mathematical density, but relies on theoretical derivations and simulations without providing ready-to-use code, datasets, or rigorous backtesting results.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Estimate Parameters & Analyze<br>Asymptotics in CIR/CKLS Models"] --> B["Methodology:<br>Euler-Maruyama Discretization of SDEs"]
  B --> C["Computational Process:<br>Linear Regression on<br>Discretized Equations"]
  C --> D{"Key Outcomes"}
  D --> E["Theoretical Guarantees:<br>Strong Consistency &<br>Asymptotic Normality"]
  D --> F["Boundary Analysis:<br>Unattainability at Zero/Infinity<br>via Scale/Speed Functions"]
  D --> G["Stationarity:<br>Existence & Density of<br>Stationary Distribution"]

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 using Euler‑Maruyama discretization to transform the CKLS SDE into a linear‑regression form for efficient parameter estimation, and establishes strong consistency and asymptotic normality of the drift and volatility estimators.

Source sentence
We employ Euler-Maruyama discretization to transform the continuous-time stochastic differential equations (SDEs) of these models into a discretized form that facilitates efficient simulation and estimation of parameters using linear regression techniques. We established the strong consistency and asymptotic normality of the estimators for the drift and volatility parameters, providing a theoretical underpinning for

Assumes 3

  • All model parameters β1, β2, and σ are strictly positive. model
    Source sentence
    2 Preliminaries and the Theoretical Results Throughout this paper the following basic assumptions are taken to avoid degenerated parameter cases, Assumption: (i) All the parameters β1, β2, σ are strictly positive.
  • The initial value of the process r0 is positive. model
    Source sentence
    (ii) Initial value of the process, r0 > 0.
  • The diffusion exponent α lies in the interval [0.5, 1]. model
    Source sentence
    Now consider the sde, drt = (β1 −β2rt)dt + σrα t dWt (1) where α ∈[0.5, 1], for the CKLS model.

Data

  • Simulated CKLS paths synthetic public
    Source sentence
    Within each block defined by a fixed “Initial Value” and α, the table clearly contrasts the actual parameter values — denoted by β1, β2, and σ — with their corresponding estimates ˆβ1, ˆβ2, and ˆσ. This layout facilitates direct comparison and allows the reader to assess the estimation accuracy under varying conditions.

Costs

Not applicable The paper reports no trading or execution result.

Finds 5

  • The estimators for drift and volatility parameters are strongly consistent and asymptotically normal. theoretical
    Source sentence
    We established the strong consistency and asymptotic normality of the estimators for the drift and volatility parameters, providing a theoretical underpinning for the parameter estimation process.
  • Under the basic assumptions, the CKLS process has an unattainable boundary at zero (except for α = 1 with an extra condition). theoretical
    Source sentence
    (1) converges to a stationary distri-bution, and the boundary at 0 remains unattainable in all cases, except for the special case α = 1 2. In this scenario, an additional condition, 2β1 > σ2, is required to ensure the boundary at 0 is unattainable.
  • Sufficient conditions for the existence of a stationary distribution are derived, with explicit stationary density formulas for different α regimes. theoretical
    Source sentence
    The stationary distribution is given by: f(r) = C(α)r−2α exp(Q(r; α)), C(α)−1 = Z ∞ 0 r−2α exp(Q(r; α)) dr, (2) where the function Q(r; α) is defined as follows: For 1 2 < α < 1 : Q(r; α) = 2β2 σ2  β1r1−2α β2(1 −2α) −r2−2α 2 −2α  For α = 1 2 : Q(r; α) = 2β2 σ2 β1 β2 ln r −r  For α = 1 : Q(r; α) = 2β2 σ2  −β1 β2r −ln r  Proof.
  • Simulation results show that the volatility parameter σ̂ can be estimated with high accuracy and stability across sample sizes. statistical
    Source sentence
    11 Our simulation results demonstrate that the volatility parameter ˆσ can be estimated with high accuracy and stability across different sample sizes.
  • The drift parameters β̂1 and β̂2 converge more slowly, with β̂2 especially sensitive to the initial condition of the process. statistical
    Source sentence
    However, the drift parameters ˆβ1 and ˆβ2 converge more slowly, with the latter exhibiting notable sensitivity to the process’s initial condition.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 33 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 (25)

  1. Convergence of an Euler scheme for a hybrid stochastic-local volatility model with stochastic rates in foreign exchange markets (2016) — link
  2. An Euler-type method for the strong approximation of the Cox–Ingersoll–Ross process (2012) — link
  3. An Empirical Comparison of Alternative Models of the Short-Term Interest Rate (1992) — link
  4. A Theory of the Term Structure of Interest Rates (1985)
  5. Estimation for Continuous Branching Processes (1998)
  6. Asymptotic properties of estimators in a stable Cox-Ingersoll-Ross model (2013) — link
  7. Bayesian Estimation of CIR Model (2022) — link
  8. Asymptotic properties of maximum likelihood estimator for the growth rate of a stable CIR process based on continuous time observations (2019) — link
and 17 more
  1. Asymptotic Behavior of the Maximum Likelihood Estimator for Ergodic and Nonergodic Square-Root Diffusions (2013) — link
  2. Parameter Estimation for the Square-Root Diffusions: Ergodic and Nonergodic Cases (2012) — link
  3. A Nonparametric Model of Term Structure Dynamics and the Market Price of Interest Rate Risk (1997) — link
  4. A nonparametric approach to the estimation of diffusion processes, with an application to a short-term interest rate model (1996)
  5. Efficient Algorithms for Estimation in Diffusion Processes (1995)
  6. Martingale estimation functions for discretely observed diffusion processes (1995)
  7. Two methods of estimation of the drift parameters of the Cox–Ingersoll–Ross process: Continuous observations (2022) — link
  8. Parameter estimation in CKLS model by continuous observations (2022) — link
  9. Inference for Stochastic Processes by Yuri A. Kutoyants (Book Review) (2005)
  10. The valuation of options for alternative stochastic processes (1976)
  11. Moment Explosions in Stochastic Volatility Models (2007) — link
  12. A second course in stochastic processes (1981) — link
  13. Quasi-Likelihood And Its Application (2008) — link
  14. Statistical Inference for Ergodic Diffusion Processes (2013) — link
  15. Essentials of Stochastic Processes (2016) — link
  16. Asymptotic Methods in the Theory of Stochastic Differential Equations (2009) — link
  17. Brownian Motion and Stochastic Calculus (1991) — link

0 of 25 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.