Parameter estimation in stochastic differential equations with Markov chain Monte Carlo and non-linear Kalman filtering

This paper is concerned with parameter estimation in linear and non-linear Itô type stochastic differential equations using Markov chain Monte Carlo (MCMC) methods. The MCMC methods studied in this paper are the Metropolis–Hastings and Hamiltonian Monte Carlo (HMC) algorithms. In these kind of models, the computation of the energy function gradient needed by HMC and gradient based optimization methods is non-trivial, and here we show how the gradient can be computed with a linear or non-linear Kalman filter-like recursion. We shall also show how in the linear case the differential equations in the gradient recursion equations can be solved using the matrix fraction decomposition. Numerical results for simulated examples are presented and discussed in detail.

[1]  Yacine Aït-Sahalia.  Maximum Likelihood Estimation of Discretely Sampled Diffusions: A Closed‐form Approximation Approach , 2002 .

[2]  Simo Särkkä,et al.  Recursive Bayesian inference on stochastic differential equations , 2006 .

[3]  Hermann Singer.  Continuous-discrete state-space modeling of panel data with nonlinear filter algorithms , 2011 .

[4]  P. Fearnhead,et al.  Exact and computationally efficient likelihood‐based estimation for discretely observed diffusion processes (with discussion) , 2006 .

[5]  Ioannis Karatzas,et al.  Brownian Motion and Stochastic Calculus , 1987 .

[6]  Darren J. Wilkinson,et al.  Bayesian sequential inference for nonlinear multivariate diffusions , 2006, Stat. Comput..

[7]  Darren J. Wilkinson,et al.  Bayesian inference for nonlinear multivariate diffusion models observed with error , 2008, Comput. Stat. Data Anal..

[8]  Jerry Nedelman,et al.  Book review: “Bayesian Data Analysis,” Second Edition by A. Gelman, J.B. Carlin, H.S. Stern, and D.B. Rubin Chapman & Hall/CRC, 2004 , 2005, Comput. Stat..

[9]  Ola Elerian,et al.  A note on the existence of a closed form conditional transition density for the Milstein scheme , 1998 .

[10]  Radford M. Neal.  MCMC Using Hamiltonian Dynamics , 2011, 1206.1901.

[11]  A. Pedersen.  A new approach to maximum likelihood estimation for stochastic differential equations based on discrete observations , 1995 .

[12]  Mohinder S. Grewal,et al.  Kalman Filtering: Theory and Practice Using MATLAB , 2001 .

[13]  Lingyu Chen,et al.  Exploring Hybrid Monte Carlo in Bayesian Computation , 2000 .

[14]  Jouko Lampinen,et al.  Rao-Blackwellized particle filter for multiple target tracking , 2007, Inf. Fusion.

[15]  Eric Moulines,et al.  Inference in hidden Markov models , 2010, Springer series in statistics.

[16]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[17]  A. Jazwinski.  Stochastic Processes and Filtering Theory , 1970 .

[18]  Rolf Poulsen,et al.  Transition Densities of Diffusion Processes , 2002 .

[19]  Charles J. Geyer,et al.  Practical Markov Chain Monte Carlo , 1992 .

[20]  N. Shephard,et al.  Likelihood INference for Discretely Observed Non-linear Diffusions , 2001 .

[21]  Jan Nygaard Nielsen,et al.  Parameter estimation in stochastic differential equations: An overview , 2000 .

[22]  Jeffrey K. Uhlmann,et al.  Unscented filtering and nonlinear estimation , 2004, Proceedings of the IEEE.

[23]  P. Kloeden,et al.  Numerical Solution of Stochastic Differential Equations , 1992 .

[24]  Timothy F. Havel,et al.  Derivatives of the Matrix Exponential and Their Computation , 1995 .

[25]  Bjørn Eraker.  MCMC Analysis of Diffusion Models With Application to Finance , 2001 .

[26]  O. Stramer,et al.  Bayesian inference for irreducible diffusion processes using the pseudo-marginal approach , 2011 .

[27]  K. Lindsay,et al.  Estimating the parameters of stochastic differential equations , 1999 .

[28]  R. Carroll,et al.  Advanced Markov Chain Monte Carlo Methods: Learning from Past Samples , 2010 .

[29]  B. Øksendal.  Stochastic differential equations : an introduction with applications , 1987 .

[30]  Simo Särkkä,et al.  On Unscented Kalman Filtering for State Estimation of Continuous-Time Nonlinear Systems , 2007, IEEE Trans. Autom. Control..

[31]  J. Berger.  Statistical Decision Theory and Bayesian Analysis , 1988 .

[32]  Hermann Singer.  Parameter Estimation of Nonlinear Stochastic Differential Equations: Simulated Maximum Likelihood versus Extended Kalman Filter and Itô-Taylor Expansion , 2002 .

[33]  Christopher S. Jones,et al.  A Simple Bayesian Method for the Analysis of Diffusion Processes , 1998 .

[34]  J. Butcher.  Numerical Methods for Ordinary Differential Equations: Butcher/Numerical Methods , 2005 .

[35]  Hermann Singer.  A survey of estimation methods for stochastic differential equastions , 2004 .

[36]  Yacine Aït-Sahalia.  Closed-Form Likelihood Expansions for Multivariate Diffusions , 2008 .

[37]  Stan Hurn,et al.  On the Efficacy of Simulated Maximum Likelihood for Estimating the Parameters of Stochastic Differential Equation , 2003 .

[38]  Peter Young,et al.  Parameter estimation for continuous-time models - A survey , 1979, Autom..

[39]  Paul Schneider,et al.  Bayesian inference for discretely sampled Markov processes with closed-form likelihood expansions , 2010 .

[40]  Tohru Ozaki,et al.  Estimation for nonlinear stochastic differential equations by a local linearization method 1 , 1998 .

[41]  G. Roberts,et al.  Monte Carlo Maximum Likelihood Estimation for Discretely Observed Diffusion Processes , 2009, 0903.0290.

[42]  G. Uhlenbeck,et al.  On the Theory of the Brownian Motion , 1930 .

[43]  J. Jeisman.  Estimation of the parameters of stochastic differential equations , 2006 .

[44]  Sebastian Reich,et al.  Explicit variable step-size and time-reversible integration , 2001 .

[45]  Hai-Xiang Lin,et al.  Probability density estimation in stochastic environmental models using reverse representations , 2003 .

[46]  Brett Ninness,et al.  Bayesian system identification via Markov chain Monte Carlo techniques , 2010, Autom..

[47]  J. M. Sanz-Serna,et al.  Optimal tuning of the hybrid Monte Carlo algorithm , 2010, 1001.4460.

[48]  Sylvia Richardson,et al.  Markov Chain Monte Carlo in Practice , 1997 .

[49]  A. Doucet,et al.  Particle Markov chain Monte Carlo methods , 2010 .

[50]  S. Duane,et al.  Hybrid Monte Carlo , 1987 .

[51]  J. Butcher.  Numerical methods for ordinary differential equations , 2003 .

[52]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[53]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[54]  Christophe Andrieu,et al.  A tutorial on adaptive MCMC , 2008, Stat. Comput..

[55]  H. Sørensen.  Parametric Inference for Diffusion Processes Observed at Discrete Points in Time: a Survey , 2004 .

[56]  Michael W. Brandt,et al.  Simulated Likelihood Estimation of Diffusions with an Application to Exchange Rate Dynamics in Incomplete Markets , 2001 .