Statistics and Computing

, Volume 22, Issue 1, pp 205–217

Approximation of transition densities of stochastic differential equations by saddlepoint methods applied to small-time Ito–Taylor sample-path expansions

Authors

    • Division of Statistics, School of Mathematical SciencesUniversity of Nottingham
  • Andrew T. A. Wood
    • Division of Statistics, School of Mathematical SciencesUniversity of Nottingham
Article

DOI: 10.1007/s11222-010-9218-8

Cite this article as:
Preston, S.P. & Wood, A.T.A. Stat Comput (2012) 22: 205. doi:10.1007/s11222-010-9218-8

Abstract

Likelihood-based inference for parameters of stochastic differential equation (SDE) models is challenging because for most SDEs the transition density is unknown. We propose a method for estimating the transition density that involves expanding the sample path as an Ito–Taylor series, calculating the moment generating function of the retained terms in the Ito–Taylor expansion, then employing a saddlepoint approximation. We perform a numerical comparison with two other methods similarly based on small-time expansions and discuss the pros and cons of our new method relative to other approaches.

Keywords

Ito–Taylor expansionSaddlepoint approximationStochastic differential equationTransition density

Copyright information

© Springer Science+Business Media, LLC 2011