Quick and easy one-step parameter estimation in differential equations

Peter Hall, Yanyuan Ma

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Differential equations are customarily used to describe dynamic systems. Existing methods for estimating unknown parameters in those systems include parameter cascade, which is a spline-based technique, and pseudo-least-squares, which is a local-polynomial-based two-step method. Parameter cascade is often referred to as a 'one-step method', although it in fact involves at least two stages: one to choose the tuning parameter and another to select model parameters. We propose a class of fast, easy-to-use, genuinely one-step procedures for estimating unknown parameters in dynamic system models. This approach does not need extraneous estimation of the tuning parameter; it selects that quantity, as well as all the model parameters, in a single explicit step, and it produces root-n-consistent estimators of all the model parameters. Although it is of course not as accurate as more complex methods, its speed and ease of use make it particularly attractive for exploratory data analysis.

Original languageEnglish (US)
Pages (from-to)735-748
Number of pages14
JournalJournal of the Royal Statistical Society. Series B: Statistical Methodology
Volume76
Issue number4
DOIs
StatePublished - Sep 2014

Fingerprint

Parameter Estimation
Differential equation
Parameter Tuning
Unknown Parameters
Cascade
Dynamic Systems
Exploratory Data Analysis
One-step Method
Local Polynomial
Two-step Method
Consistent Estimator
Model
Spline
Least Squares
Choose
Differential equations
Parameter estimation
Roots

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{c020ba5102304725a4dfadaa4fab5176,
title = "Quick and easy one-step parameter estimation in differential equations",
abstract = "Differential equations are customarily used to describe dynamic systems. Existing methods for estimating unknown parameters in those systems include parameter cascade, which is a spline-based technique, and pseudo-least-squares, which is a local-polynomial-based two-step method. Parameter cascade is often referred to as a 'one-step method', although it in fact involves at least two stages: one to choose the tuning parameter and another to select model parameters. We propose a class of fast, easy-to-use, genuinely one-step procedures for estimating unknown parameters in dynamic system models. This approach does not need extraneous estimation of the tuning parameter; it selects that quantity, as well as all the model parameters, in a single explicit step, and it produces root-n-consistent estimators of all the model parameters. Although it is of course not as accurate as more complex methods, its speed and ease of use make it particularly attractive for exploratory data analysis.",
author = "Peter Hall and Yanyuan Ma",
year = "2014",
month = "9",
doi = "10.1111/rssb.12040",
language = "English (US)",
volume = "76",
pages = "735--748",
journal = "Journal of the Royal Statistical Society. Series B: Statistical Methodology",
issn = "1369-7412",
publisher = "Wiley-Blackwell",
number = "4",

}

Quick and easy one-step parameter estimation in differential equations. / Hall, Peter; Ma, Yanyuan.

In: Journal of the Royal Statistical Society. Series B: Statistical Methodology, Vol. 76, No. 4, 09.2014, p. 735-748.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Quick and easy one-step parameter estimation in differential equations

AU - Hall, Peter

AU - Ma, Yanyuan

PY - 2014/9

Y1 - 2014/9

N2 - Differential equations are customarily used to describe dynamic systems. Existing methods for estimating unknown parameters in those systems include parameter cascade, which is a spline-based technique, and pseudo-least-squares, which is a local-polynomial-based two-step method. Parameter cascade is often referred to as a 'one-step method', although it in fact involves at least two stages: one to choose the tuning parameter and another to select model parameters. We propose a class of fast, easy-to-use, genuinely one-step procedures for estimating unknown parameters in dynamic system models. This approach does not need extraneous estimation of the tuning parameter; it selects that quantity, as well as all the model parameters, in a single explicit step, and it produces root-n-consistent estimators of all the model parameters. Although it is of course not as accurate as more complex methods, its speed and ease of use make it particularly attractive for exploratory data analysis.

AB - Differential equations are customarily used to describe dynamic systems. Existing methods for estimating unknown parameters in those systems include parameter cascade, which is a spline-based technique, and pseudo-least-squares, which is a local-polynomial-based two-step method. Parameter cascade is often referred to as a 'one-step method', although it in fact involves at least two stages: one to choose the tuning parameter and another to select model parameters. We propose a class of fast, easy-to-use, genuinely one-step procedures for estimating unknown parameters in dynamic system models. This approach does not need extraneous estimation of the tuning parameter; it selects that quantity, as well as all the model parameters, in a single explicit step, and it produces root-n-consistent estimators of all the model parameters. Although it is of course not as accurate as more complex methods, its speed and ease of use make it particularly attractive for exploratory data analysis.

UR - http://www.scopus.com/inward/record.url?scp=84905825520&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905825520&partnerID=8YFLogxK

U2 - 10.1111/rssb.12040

DO - 10.1111/rssb.12040

M3 - Article

AN - SCOPUS:84905825520

VL - 76

SP - 735

EP - 748

JO - Journal of the Royal Statistical Society. Series B: Statistical Methodology

JF - Journal of the Royal Statistical Society. Series B: Statistical Methodology

SN - 1369-7412

IS - 4

ER -