Theoretical Limitations of Allan Variance-based Regression for Time Series Model Estimation

Stephane Guerrier, Roberto Molinari, Yannick Stebler

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

This letter formally proves the statistical inconsistency of the Allan variance-based estimation of latent (composite) model parameters. This issue has not been sufficiently investigated and highlighted since it is a technique that is still being widely used in practice, especially within the engineering domain. Indeed, among others, this method is frequently used for inertial sensor calibration, which often deals with latent time series models and practitioners in these domains are often unaware of its limitations. To prove the inconsistency of this method, we first provide a formal definition and subsequently deliver its theoretical properties, highlighting its limitations by comparing it with another statistically sound method.

Original languageEnglish (US)
Article number7433406
Pages (from-to)595-599
Number of pages5
JournalIEEE Signal Processing Letters
Volume23
Issue number5
DOIs
StatePublished - May 1 2016

Fingerprint

Time Series Models
Time series
Regression
Inconsistency
Inertial Sensors
Acoustic waves
Calibration
Sensors
Composite materials
Composite
Engineering
Model

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

@article{244f3d0c35ce4d07ac9f249048f4e394,
title = "Theoretical Limitations of Allan Variance-based Regression for Time Series Model Estimation",
abstract = "This letter formally proves the statistical inconsistency of the Allan variance-based estimation of latent (composite) model parameters. This issue has not been sufficiently investigated and highlighted since it is a technique that is still being widely used in practice, especially within the engineering domain. Indeed, among others, this method is frequently used for inertial sensor calibration, which often deals with latent time series models and practitioners in these domains are often unaware of its limitations. To prove the inconsistency of this method, we first provide a formal definition and subsequently deliver its theoretical properties, highlighting its limitations by comparing it with another statistically sound method.",
author = "Stephane Guerrier and Roberto Molinari and Yannick Stebler",
year = "2016",
month = "5",
day = "1",
doi = "10.1109/LSP.2016.2541867",
language = "English (US)",
volume = "23",
pages = "595--599",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

Theoretical Limitations of Allan Variance-based Regression for Time Series Model Estimation. / Guerrier, Stephane; Molinari, Roberto; Stebler, Yannick.

In: IEEE Signal Processing Letters, Vol. 23, No. 5, 7433406, 01.05.2016, p. 595-599.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Theoretical Limitations of Allan Variance-based Regression for Time Series Model Estimation

AU - Guerrier, Stephane

AU - Molinari, Roberto

AU - Stebler, Yannick

PY - 2016/5/1

Y1 - 2016/5/1

N2 - This letter formally proves the statistical inconsistency of the Allan variance-based estimation of latent (composite) model parameters. This issue has not been sufficiently investigated and highlighted since it is a technique that is still being widely used in practice, especially within the engineering domain. Indeed, among others, this method is frequently used for inertial sensor calibration, which often deals with latent time series models and practitioners in these domains are often unaware of its limitations. To prove the inconsistency of this method, we first provide a formal definition and subsequently deliver its theoretical properties, highlighting its limitations by comparing it with another statistically sound method.

AB - This letter formally proves the statistical inconsistency of the Allan variance-based estimation of latent (composite) model parameters. This issue has not been sufficiently investigated and highlighted since it is a technique that is still being widely used in practice, especially within the engineering domain. Indeed, among others, this method is frequently used for inertial sensor calibration, which often deals with latent time series models and practitioners in these domains are often unaware of its limitations. To prove the inconsistency of this method, we first provide a formal definition and subsequently deliver its theoretical properties, highlighting its limitations by comparing it with another statistically sound method.

UR - http://www.scopus.com/inward/record.url?scp=84964389365&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964389365&partnerID=8YFLogxK

U2 - 10.1109/LSP.2016.2541867

DO - 10.1109/LSP.2016.2541867

M3 - Article

AN - SCOPUS:84964389365

VL - 23

SP - 595

EP - 599

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 5

M1 - 7433406

ER -