Exact Likelihood Inference and Robust Filtering for Gauss-Cauchy Convolution Models

TL;DR

This paper introduces analytical methods for the Voigt distribution, enabling stable likelihood inference and a robust filter for heavy-tailed noise in state-space models, demonstrated on financial volatility data.

Contribution

It derives explicit formulas for the Voigt distribution's density and moments, and develops the Gauss-Cauchy Convolution (GCC) filter for robust state estimation with heavy-tailed errors.

Findings

GCC filter effectively separates latent variation from measurement noise.

The approach outperforms Gaussian, Student-t, and Huber methods in volatility estimation.

Analytical expressions improve stability and efficiency of inference.

Abstract

The convolution of a Gaussian and a Cauchy distribution, known as the Voigt distribution, is widely used in spectroscopy and provides a natural framework for modeling heavy-tailed measurement noise. We derive analytical expressions for its density, score, Hessian, and conditional moments using the scaled complementary error function, enabling stable maximum likelihood estimation without numerical convolution, finite-difference derivatives, or pseudo-Voigt approximations. The conditional expectation of the latent Gaussian component is governed by a redescending location score, so extreme observations are automatically discounted rather than propagated. This structure motivates the Gauss-Cauchy Convolution (GCC) filter for state-space models with Gaussian latent dynamics and heavy-tailed measurement errors. In an application to log realized volatility for the Technology Select Sector SPDR Fund, the GCC filter separates persistent latent variation from transient measurement noise and improves on Gaussian, Student-$t$, Huber, and related robust alternatives.