On the robust utilization of non-parametric tests for evaluation of combined cyclical and monotonic drift

Paolo Cappa, Sergio Silvestri, Salvatore Andrea Sciuto

Research output: Contribution to journalArticle

Abstract

Non-parametric statistical tests are usually adopted to recognize drift phenomena in data series acquired by automatic measuring systems. Sometimes different tests provide different responses with regard to the presence of drift in data sets. In particular, the application of two commonly used statistical tests (i.e. the Wald-Wolfovitz test, also known as the run test, and the Mann-Whitney test, also known as the reverse arrangement test) to data acquired during long-term trials showed that they exhibited different behaviours regarding shift detection. Thus, a deeper examination of previously indicated statistical tests in real measurements appears of interest; more precisely their effectiveness is verified (i) when cyclical and monotonous drift are concurrently present and (ii) various levels of noise are superimposed on the data gathered. Finally, on the basis of the theoretical results obtained, the statistical tests here examined are applied to the same data set in order to validate their capability in on-line drift recognition.

Original languageEnglish
Pages (from-to)1439-1444
Number of pages6
JournalMeasurement Science and Technology
Volume12
Issue number9
DOIs
Publication statusPublished - Sep 2001

Fingerprint

Statistical tests
Non-parametric test
statistical tests
Monotonic
Statistical test
evaluation
Evaluation
Mann-Whitney test
Wald Test
Reverse
Arrangement
examination
Series
shift

Keywords

  • Cyclical and monotonic drift
  • Drift evaluation
  • Non-parametric tests
  • Reverse arrangement test
  • Run test
  • Shift detection

ASJC Scopus subject areas

  • Polymers and Plastics
  • Ceramics and Composites
  • Materials Science (miscellaneous)

Cite this

On the robust utilization of non-parametric tests for evaluation of combined cyclical and monotonic drift. / Cappa, Paolo; Silvestri, Sergio; Sciuto, Salvatore Andrea.

In: Measurement Science and Technology, Vol. 12, No. 9, 09.2001, p. 1439-1444.

Research output: Contribution to journalArticle

Cappa, Paolo ; Silvestri, Sergio ; Sciuto, Salvatore Andrea. / On the robust utilization of non-parametric tests for evaluation of combined cyclical and monotonic drift. In: Measurement Science and Technology. 2001 ; Vol. 12, No. 9. pp. 1439-1444.
@article{ae16176d4e924b919b4dee96ea7f2b1b,
title = "On the robust utilization of non-parametric tests for evaluation of combined cyclical and monotonic drift",
abstract = "Non-parametric statistical tests are usually adopted to recognize drift phenomena in data series acquired by automatic measuring systems. Sometimes different tests provide different responses with regard to the presence of drift in data sets. In particular, the application of two commonly used statistical tests (i.e. the Wald-Wolfovitz test, also known as the run test, and the Mann-Whitney test, also known as the reverse arrangement test) to data acquired during long-term trials showed that they exhibited different behaviours regarding shift detection. Thus, a deeper examination of previously indicated statistical tests in real measurements appears of interest; more precisely their effectiveness is verified (i) when cyclical and monotonous drift are concurrently present and (ii) various levels of noise are superimposed on the data gathered. Finally, on the basis of the theoretical results obtained, the statistical tests here examined are applied to the same data set in order to validate their capability in on-line drift recognition.",
keywords = "Cyclical and monotonic drift, Drift evaluation, Non-parametric tests, Reverse arrangement test, Run test, Shift detection",
author = "Paolo Cappa and Sergio Silvestri and Sciuto, {Salvatore Andrea}",
year = "2001",
month = "9",
doi = "10.1088/0957-0233/12/9/309",
language = "English",
volume = "12",
pages = "1439--1444",
journal = "Measurement Science and Technology",
issn = "0957-0233",
publisher = "IOP Publishing Ltd.",
number = "9",

}

TY - JOUR

T1 - On the robust utilization of non-parametric tests for evaluation of combined cyclical and monotonic drift

AU - Cappa, Paolo

AU - Silvestri, Sergio

AU - Sciuto, Salvatore Andrea

PY - 2001/9

Y1 - 2001/9

N2 - Non-parametric statistical tests are usually adopted to recognize drift phenomena in data series acquired by automatic measuring systems. Sometimes different tests provide different responses with regard to the presence of drift in data sets. In particular, the application of two commonly used statistical tests (i.e. the Wald-Wolfovitz test, also known as the run test, and the Mann-Whitney test, also known as the reverse arrangement test) to data acquired during long-term trials showed that they exhibited different behaviours regarding shift detection. Thus, a deeper examination of previously indicated statistical tests in real measurements appears of interest; more precisely their effectiveness is verified (i) when cyclical and monotonous drift are concurrently present and (ii) various levels of noise are superimposed on the data gathered. Finally, on the basis of the theoretical results obtained, the statistical tests here examined are applied to the same data set in order to validate their capability in on-line drift recognition.

AB - Non-parametric statistical tests are usually adopted to recognize drift phenomena in data series acquired by automatic measuring systems. Sometimes different tests provide different responses with regard to the presence of drift in data sets. In particular, the application of two commonly used statistical tests (i.e. the Wald-Wolfovitz test, also known as the run test, and the Mann-Whitney test, also known as the reverse arrangement test) to data acquired during long-term trials showed that they exhibited different behaviours regarding shift detection. Thus, a deeper examination of previously indicated statistical tests in real measurements appears of interest; more precisely their effectiveness is verified (i) when cyclical and monotonous drift are concurrently present and (ii) various levels of noise are superimposed on the data gathered. Finally, on the basis of the theoretical results obtained, the statistical tests here examined are applied to the same data set in order to validate their capability in on-line drift recognition.

KW - Cyclical and monotonic drift

KW - Drift evaluation

KW - Non-parametric tests

KW - Reverse arrangement test

KW - Run test

KW - Shift detection

UR - http://www.scopus.com/inward/record.url?scp=0035447487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035447487&partnerID=8YFLogxK

U2 - 10.1088/0957-0233/12/9/309

DO - 10.1088/0957-0233/12/9/309

M3 - Article

AN - SCOPUS:0035447487

VL - 12

SP - 1439

EP - 1444

JO - Measurement Science and Technology

JF - Measurement Science and Technology

SN - 0957-0233

IS - 9

ER -