Sparse Kalman Filtering Approaches to Covariance Estimation from High Frequency Data in the Presence of Jumps

TL;DR

This paper extends Kalman filtering techniques to better estimate asset return covariance matrices from high frequency data by incorporating jump detection and sparse modeling, improving accuracy over existing methods.

Contribution

The paper introduces two novel sparse Kalman filtering approaches that incorporate jump detection and Bayesian sampling for covariance estimation in high frequency data.

Findings

Improved covariance estimation accuracy with jump models

Effective jump detection using sparse Kalman filtering

Bayesian approach provides posterior distribution insights

Abstract

Estimation of the covariance matrix of asset returns from high frequency data is complicated by asynchronous returns, market mi- crostructure noise and jumps. One technique for addressing both asynchronous returns and market microstructure is the Kalman-EM (KEM) algorithm. However the KEM approach assumes log-normal prices and does not address jumps in the return process which can corrupt estimation of the covariance matrix. In this paper we extend the KEM algorithm to price models that include jumps. We propose two sparse Kalman filtering approaches to this problem. In the first approach we develop a Kalman Expectation Conditional Maximization (KECM) algorithm to determine the un- known covariance as well as detecting the jumps. For this algorithm we consider Laplace and the spike and slab jump models, both of which promote sparse estimates of the jumps. In the second method we take a Bayesian approach and use Gibbs sampling to sample from the posterior distribution of the covariance matrix under the spike and slab jump model. Numerical results using simulated data show that each of these approaches provide for improved covariance estima- tion relative to the KEM method in a variety of settings where jumps occur.