×

Inference in dynamic systems using B-splines and quasilinearized ODE penalties. (English) Zbl 1386.62011

Summary: Nonlinear (systems of) ordinary differential equations (ODEs) are common tools in the analysis of complex one-dimensional dynamic systems. We propose a smoothing approach regularized by a quasilinearized ODE-based penalty. Within the quasilinearized spline-based framework, the estimation reduces to a conditionally linear problem for the optimization of the spline coefficients. Furthermore, standard ODE compliance parameter(s) selection criteria are applicable. We evaluate the performances of the proposed strategy through simulated and real data examples. Simulation studies suggest that the proposed procedure ensures more accurate estimates than standard nonlinear least squares approaches when the state (initial and/or boundary) conditions are not known.

MSC:

62G07 Density estimation
65D10 Numerical smoothing, curve fitting

Software:

FITPACK
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Bellman, Quasilinearization and Nonlinear Boundary-value Problems (1965) · Zbl 0139.10702
[2] Biegler, Nonlinear parameter estimation: a case study comparison, AIChE Journal 32 pp 29– (1986) · JFM 19.0271.02
[3] Currie, Smoothing constrained generalized linear models with an application to the Lee-Carter model, Statistical Modelling 13 pp 69– (2013)
[4] Dierckx, Curve and Surface Fitting with Splines (1995) · Zbl 0932.41010
[5] Santos, Rhythm synchronization and chaotic modulation of coupled van der pol oscillators in a model for the heartbeat, Physica A: Statistical Mechanics and Its Applications 338 pp 335– (2004)
[6] Eilers, Flexible smoothing with B-splines and penalties, Statistical Science 11 pp 89– (1996) · Zbl 0955.62562
[7] Eilers, Splines, knots, and penalties, Wiley Interdisciplinary Reviews: Computational Statistics 2 pp 637– (2010)
[8] Elton, The ten-year cycle in numbers of the lynx in canada, Journal of Animal Ecology 11 pp 215– (1942)
[9] Formaggia, Cardiovascular Mathematics: Modeling and Simulation of the Circulatory System (2010)
[10] Frasso, Parameter estimation and inference in dynamic systems described by linear partial differential equations, AStA Advances in Statistical Analysis pp 1– (2015)
[11] Golub, Scientific Computing and Differential Equations (1992)
[12] Hastie, Generalized Additive Models (1990) · Zbl 0747.62061
[13] Holling, The components of predation as revealed by a study of small mammal predation predation of the european pine sawfly, Canadian Entomologist 91 pp 293– (1959)
[14] Hotelling, Differential equations subject to error, and population estimates, Journal of the American Statistical Association 22 pp 283– (1927) · JFM 53.0523.18
[15] Jaeger, Bayesian P-spline estimation in hierarchical models specified by systems of affine differential equations, Statistical Modelling 13 pp 3– (2013)
[16] MacLulich, Fluctuations in the Numbers of Varying hare (Lepus americanus) (1937)
[17] Ramsay, Parameter estimation for differential equations: a generalized smoothing approach, Journal of the Royal Statistical Society, Series B 69 pp 741– (2007)
[18] Rodriguez-Fernandez, Novel metaheuristic for parameter estimation in nonlinear dynamic biological systems, BMC Bioinformatics 7 pp 483– (2006)
[19] Schall, Estimation in generalized linear models with random effects, Biometrika 78 pp 719– (1991) · Zbl 0850.62561
[20] der Pol, On relaxation-oscillations, The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science 7 pp 978– (1926)
[21] der Pol, The heartbeat considered as a relaxation oscillation, and an electrical model of the heart, Philosophical Magazine Series 7 6 pp 763– (1928)
[22] Wahba, Spline Models for Observational Data, volume 59 of CBMS-NSF Regional Conference Series in Applied Mathematics (1990) · Zbl 0813.62001
[23] Wu, Parameter identifiability and estimation of hiv/aids dynamic models, Bulletin of Mathematical Biology 70 pp 785– (2008) · Zbl 1146.92021
[24] Xue, Sieve estimation of constant and time-varying coefficients in nonlinear ordinary differential equation models by considering both numerical error and measurement error, Analytical Statistics 38 pp 2351– (2010) · Zbl 1203.62049
[25] Zhang, Factors affecting hare-lynx dynamics in the classic time series of the Hudson Bay Company, Canada, Climate Research 34 pp 83– (2007)
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.