Appraising Model Complexity in Option Pricing

Abstract

The research question we consider is whether incremental complexity in option pricing models is justified by incremental model performance. We apply the model confidence set as a formal model comparison approach in appraising stochastic volatility jump-diffusion option pricing models, spanning affine and nonaffine specifications. Jumps in price with stochastic (constant) arrival intensity produce superior (inferior) outcomes. A parsimonious negative exponential price jump distribution outperforms the popular normal distribution. Jumps in volatility (synchronized or not) worsen model performance. A parsimonious nonlinear hyperbolic drift extension of the Heston model performs particularly well. Nonlinear CEV models generally do not produce appreciable model performance.