Dynamic Skewness in Stochastic Volatility Models: A Penalized Prior Approach

2025-08-14

AI Summary

Financial time series often exhibit skewness and heavy tails, rendering conventional static skewness models inadequate for capturing their dynamic heteroskedasticity. To address this, we propose a novel class of dynamic skewness stochastic volatility models based on the scale-mixture of skew-normal (SMSN) distribution family. A key innovation is the incorporation of penalized priors, which jointly promote model flexibility and parsimony while mitigating overfitting and enhancing robustness. Bayesian estimation is conducted via Hamiltonian Monte Carlo (implemented in RStan), and model performance is rigorously evaluated using DIC, WAIC, and LOO-CV. Simulation studies demonstrate that the proposed penalized priors consistently outperform standard alternatives across diverse specifications. Empirical analysis on cryptocurrency return data confirms substantial improvements in both in-sample fit and out-of-sample forecasting accuracy. The framework thus provides a theoretically rigorous and practically applicable advancement for financial volatility modeling.

Technology Category

• Reasoning under Uncertainty: Stochastic Optimization
• Machine Learning: Bayesian Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: User model development and evaluation
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Financial time series often exhibit skewness and heavy tails, making it essential to use models that incorporate these characteristics to ensure greater reliability in the results. Furthermore, allowing temporal variation in the skewness parameter can bring significant gains in the analysis of this type of series. However, for more robustness, it is crucial to develop models that balance flexibility and parsimony. In this paper, we propose dynamic skewness stochastic volatility models in the SMSN family (DynSSV-SMSN), using priors that penalize model complexity. Parameter estimation was carried out using the Hamiltonian Monte Carlo (HMC) method via the exttt{RStan} package. Simulation results demonstrated that penalizing priors present superior performance in several scenarios compared to the classical choices. In the empirical application to returns of cryptocurrencies, models with heavy tails and dynamic skewness provided a better fit to the data according to the DIC, WAIC, and LOO-CV information criteria.

Problem

• Modeling dynamic skewness in financial time series
• Balancing model flexibility with parsimony
• Improving volatility forecasts for heavy-tailed distributions

Innovation

• Dynamic skewness stochastic volatility models
• Penalized priors for model complexity
• Hamiltonian Monte Carlo parameter estimation