×

A penalized simulated maximum likelihood method to estimate parameters for SDEs with measurement error. (English) Zbl 1417.62235

Summary: The penalized simulated maximum likelihood (PSML) approach can be used to estimate parameters for a stochastic differential equation model based on completely or partially observed discrete-time observations. The PSML uses an auxiliary variable importance sampler and parameters are estimated in a penalized maximum likelihood framework. In this paper, we extend the PSML to allow for measurement error, including unknown initial conditions. Simulation studies for two stochastic models and a real world example aimed at understanding the dynamics of chronic wasting disease illustrate that our method has favorable performance in the presence of measurement error. PSML reduces both the bias and root mean squared error as compared to existing methods. Lastly, we establish consistency and asymptotic normality for the proposed estimators.

MSC:

62M05 Markov processes: estimation; hidden Markov models
60H10 Stochastic ordinary differential equations (aspects of stochastic analysis)
62F12 Asymptotic properties of parametric estimators
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Aït-Sahalia Y (2002) Transition densities for interest rate and other nonlinear diffusions. J Finance 54(4):1361-1395 · doi:10.1111/0022-1082.00149
[2] Aït-Sahalia Y (2008) Closed-form likelihood expansions for multivariate diffusions. Ann Stat 2(36):906-937 · Zbl 1246.62180 · doi:10.1214/009053607000000622
[3] Bengtsson T, Snyder C, Nychka D (2003) Toward a nonlinear ensemble filter for high-dimensional systems. J Geophys Res 108(D24):8775. https://doi.org/10.1029/2002JD002900
[4] Billingsley P (1961) Statistical inference for Markov processes, vol 2. University of Chicago Press, Chicago · Zbl 0106.34201
[5] Donnet S, Foulley J-L, Samson A (2010) Bayesian analysis of growth curves using mixed models defined by stochastic differential equations. Biometrics 66(3):733-741 · Zbl 1203.62187 · doi:10.1111/j.1541-0420.2009.01342.x
[6] Durham G, Gallant A (2002) Numerical techniques for maximum likelihood estimation of continuous-time diffusion processes. J Bus Econ Stat 20(3):297-338 · doi:10.1198/073500102288618397
[7] Eraker B (2001) MCMC analysis of diffusion models with application to finance. J Bus Econ Stat 19(2):177-191 · doi:10.1198/073500101316970403
[8] Fuchs C (2013) Inference for diffusion processes: with applications in life sciences. Springer, New York · Zbl 1276.62051 · doi:10.1007/978-3-642-25969-2
[9] Geremia C, Miller MW, Hoeting JA, Antolin MF, Hobbs NT (2015) Bayesian modeling of prion disease dynamics in mule deer using population monitoring and capture-recapture data. PloS One 10(10):e0140687 · doi:10.1371/journal.pone.0140687
[10] Golightly A, Wilkinson DJ (2005) Bayesian inference for stochastic kinetic models using a diffusion approximation. Biometrics 61(3):781-788 · Zbl 1079.62110 · doi:10.1111/j.1541-0420.2005.00345.x
[11] Golightly A, Wilkinson DJ (2006) Bayesian sequential inference for nonlinear multivariate diffusions. Stat Comput 16(4):323-338 · doi:10.1007/s11222-006-9392-x
[12] Golightly A, Wilkinson DJ (2008) Bayesian inference for nonlinear multivariate diffusion models observed with error. Comput Stat Data Anal 52(3):1674-1693 · Zbl 1452.62603 · doi:10.1016/j.csda.2007.05.019
[13] Golightly A, Wilkinson DJ (2011) Bayesian parameter inference for stochastic biochemical network models using particle Markov chain Monte Carlo. Interface Focus 1(6):807-820 · doi:10.1098/rsfs.2011.0047
[14] Kloeden P, Platen E (1992) Numerical solution of stochastic differential equations. Springer, New York · Zbl 0752.60043 · doi:10.1007/978-3-662-12616-5
[15] Lindström E (2012) A regularized bridge sampler for sparsely sampled diffusions. Stat Comput 22(2):615-623 · Zbl 1322.62211 · doi:10.1007/s11222-011-9255-y
[16] Lorenz EN (1963) Deterministic nonperiodic flow. J Atmos Sci 20(2):130-141 · Zbl 1417.37129 · doi:10.1175/1520-0469(1963)020<0130:DNF>2.0.CO;2
[17] Miller M, Hobbs N, Tavener S (2006) Dynamics of prion disease transmission in mule deer. Ecol Appl 16(6):2208-2214 · doi:10.1890/1051-0761(2006)016[2208:DOPDTI]2.0.CO;2
[18] Pedersen A (1995a) Consistency and asymptotic normality of an approximate maximum likelihood estimator for discretely observed diffusion processes. Bernoulli 1(3):257-279 · Zbl 0839.62079 · doi:10.2307/3318480
[19] Pedersen A (1995b) A new approach to maximum likelihood estimation for stochastic differential equations based on discrete observations. Scand J Stat 22(1):55-71 · Zbl 0827.62087
[20] Pitt MK, Shephard N (1999) Filtering via simulation: auxiliary particle filters. J Am Stat Assoc 94(446):590-599 · Zbl 1072.62639 · doi:10.1080/01621459.1999.10474153
[21] Särkkä S, Sottinen T (2008) Application of Girsanov theorem to particle filtering of discretely observed continuous-time non-linear systems. Bayesian Anal 3(3):555-584 · Zbl 1330.93230 · doi:10.1214/08-BA322
[22] Stramer O, Yan J (2007) On simulated likelihood of discretely observed diffusion processes and comparison to closed-form approximation. J Comput Graph Stat 16(3):672-691 · doi:10.1198/106186007X237306
[23] Sun L, Lee C, Hoeting JA (2015a) Parameter inference and model selection in deterministic and stochastic dynamical models via approximate Bayesian computation: modeling a wildlife epidemic. Environmetrics 26(7):451-462 · doi:10.1002/env.2353
[24] Sun L, Lee C, Hoeting JA (2015b) A penalized simulated maximum likelihood approach in parameter estimation for stochastic differential equations. Comput Stat Data Anal 84:54-67 · Zbl 1507.62162 · doi:10.1016/j.csda.2014.11.007
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.