Latent Jump Diffusion Factor Estimation for Commodity Futures

47 Pages Posted: 30 Jul 2015 Last revised: 18 Dec 2017

See all articles by M. A. H. Dempster

M. A. H. Dempster

University of Cambridge - Centre for Financial Research; Cambridge Systems Associates Limited; University of Cambridge - Judge Business School

Elena Medova

University of Cambridge - Centre for Financial Research; Cambridge Systems Associates Limited

Ke Tang

Tsinghua University - School of Economics & Management

Date Written: December 16, 2017

Abstract

We introduce a new methodology to estimate the latent factors of a multivariate jump diffusion process illustrated with an application to the commodity futures term structure. Specifically, we propose a new state space form and then use a modified Kalman filter to estimate models with latent jump-diffusion factors. The method is applied to oil and copper futures prices to pin down long and short term jumps in their futures term structure. Estimates of jump arrival times indicate that both important information surprises and market activities generate jumps of different intensities.

Keywords: latent factors, jumps, non-Gaussian state space models, modified Kalman filter, commodity futures

JEL Classification: G13, C58

Suggested Citation

Dempster, M. A. H. and Medova, Elena and Tang, Ke, Latent Jump Diffusion Factor Estimation for Commodity Futures (December 16, 2017). Available at SSRN: https://ssrn.com/abstract=2637567 or http://dx.doi.org/10.2139/ssrn.2637567

M. A. H. Dempster (Contact Author)

University of Cambridge - Centre for Financial Research ( email )

Centre for Mathematical Sciences
Wilberforce Road
Cambridge, CB3 0WA
United Kingdom

Cambridge Systems Associates Limited ( email )

5-7 Portugal Place
Cambridge, CB5 8AF
United Kingdom

University of Cambridge - Judge Business School ( email )

Trumpington Street
Cambridge, CB2 1AG
United Kingdom

Elena Medova

University of Cambridge - Centre for Financial Research ( email )

Centre for Mathematical Sciences
Wilberforce Road
Cambridge, CB3 0WA
United Kingdom

Cambridge Systems Associates Limited ( email )

5-7 Portugal Place
Cambridge, CB5 8AF
United Kingdom

Ke Tang

Tsinghua University - School of Economics & Management ( email )

Beijing, 100084
China

Register to save articles to
your library

Register

Paper statistics

Downloads
84
Abstract Views
482
rank
298,696
PlumX Metrics