A General Bayesian Model for Heteroskedastic Data with Fully Conjugate Full-Conditional Distributions

TL;DR

This paper introduces a flexible Bayesian model for heteroskedastic data that allows for fully conjugate priors, enabling efficient Gibbs sampling and extending to deep learning for time series and heavy-tailed data, demonstrated through three diverse applications.

Contribution

It presents a novel Bayesian heteroskedastic model with conjugate full conditional distributions, facilitating easier inference and extending to deep learning and heavy-tailed data scenarios.

Findings

Efficient Gibbs sampling enabled by conjugate priors.

Versatile modeling of heteroskedasticity with covariates and random effects.

Successful application to spatial, financial, and clinical data.

Abstract

Models for heteroskedastic data are relevant in a wide variety of applications ranging from financial time series to environmental statistics. However, the topic of modeling the variance function conditionally has not seen near as much attention as modeling the mean. Volatility models have been used in specific applications, but these models can be difficult to fit in a Bayesian setting due to posterior distributions that are challenging to sample from efficiently. In this work, we introduce a general model for heteroskedastic data. This approach models the conditional variance in a mixed model approach as a function of any desired covariates or random effects. We rely on new distribution theory in order to construct priors that yield fully conjugate full conditional distributions. Thus, our approach can easily be fit via Gibbs sampling. Furthermore, we extend the model to a deep learning approach that can provide highly accurate estimates for time dependent data. We also provide an extension for heavy-tailed data. We illustrate our methodology via three applications. The first application utilizes a high dimensional soil dataset with inherent spatial dependence. The second application involves modeling of asset volatility. The third application focuses on clinical trial data for creatinine.