Comparison of multianalyte proficiency test results by sum of ranking differences, principal component analysis, and hierarchical cluster analysis

Biljana Škrbić, K. Heberger, Nataša Crossed D Signurišić-Mladenović

Research output: Article

9 Citations (Scopus)

Abstract

Sum of ranking differences (SRD) was applied for comparing multianalyte results obtained by several analytical methods used in one or in different laboratories, i.e., for ranking the overall performances of the methods (or laboratories) in simultaneous determination of the same set of analytes. The data sets for testing of the SRD applicability contained the results reported during one of the proficiency tests (PTs) organized by EU Reference Laboratory for Polycyclic Aromatic Hydrocarbons (EU-RL-PAH). In this way, the SRD was also tested as a discriminant method alternative to existing average performance scores used to compare mutlianalyte PT results. SRD should be used along with the z scores - the most commonly used PT performance statistics. SRD was further developed to handle the same rankings (ties) among laboratories. Two benchmark concentration series were selected as reference: (a) the assigned PAH concentrations (determined precisely beforehand by the EU-RL-PAH) and (b) the averages of all individual PAH concentrations determined by each laboratory. Ranking relative to the assigned values and also to the average (or median) values pointed to the laboratories with the most extreme results, as well as revealed groups of laboratories with similar overall performances. SRD reveals differences between methods or laboratories even if classical test(s) cannot. The ranking was validated using comparison of ranks by random numbers (a randomization test) and using seven folds cross-validation, which highlighted the similarities among the (methods used in) laboratories. Principal component analysis and hierarchical cluster analysis justified the findings based on SRD ranking/grouping. If the PAH-concentrations are row-scaled, (i.e., z scores are analyzed as input for ranking) SRD can still be used for checking the normality of errors. Moreover, cross-validation of SRD on z scores groups the laboratories similarly. The SRD technique is general in nature, i.e., it can be applied to any experimental problem in which multianalyte results obtained either by several analytical procedures, analysts, instruments, or laboratories need to be compared. [Figure not available: see fulltext.]

Original languageEnglish
Pages (from-to)8363-8375
Number of pages13
JournalAnalytical and Bioanalytical Chemistry
Volume405
Issue number25
DOIs
Publication statusPublished - okt. 2013

Fingerprint

Cluster analysis
Principal Component Analysis
Principal component analysis
Cluster Analysis
Polycyclic aromatic hydrocarbons
Polycyclic Aromatic Hydrocarbons
Benchmarking
Random Allocation
Statistics

ASJC Scopus subject areas

  • Analytical Chemistry
  • Biochemistry

Cite this

Comparison of multianalyte proficiency test results by sum of ranking differences, principal component analysis, and hierarchical cluster analysis. / Škrbić, Biljana; Heberger, K.; Crossed D Signurišić-Mladenović, Nataša.

In: Analytical and Bioanalytical Chemistry, Vol. 405, No. 25, 10.2013, p. 8363-8375.

Research output: Article

@article{3347afcc618548e890fac1a603904a4a,
title = "Comparison of multianalyte proficiency test results by sum of ranking differences, principal component analysis, and hierarchical cluster analysis",
abstract = "Sum of ranking differences (SRD) was applied for comparing multianalyte results obtained by several analytical methods used in one or in different laboratories, i.e., for ranking the overall performances of the methods (or laboratories) in simultaneous determination of the same set of analytes. The data sets for testing of the SRD applicability contained the results reported during one of the proficiency tests (PTs) organized by EU Reference Laboratory for Polycyclic Aromatic Hydrocarbons (EU-RL-PAH). In this way, the SRD was also tested as a discriminant method alternative to existing average performance scores used to compare mutlianalyte PT results. SRD should be used along with the z scores - the most commonly used PT performance statistics. SRD was further developed to handle the same rankings (ties) among laboratories. Two benchmark concentration series were selected as reference: (a) the assigned PAH concentrations (determined precisely beforehand by the EU-RL-PAH) and (b) the averages of all individual PAH concentrations determined by each laboratory. Ranking relative to the assigned values and also to the average (or median) values pointed to the laboratories with the most extreme results, as well as revealed groups of laboratories with similar overall performances. SRD reveals differences between methods or laboratories even if classical test(s) cannot. The ranking was validated using comparison of ranks by random numbers (a randomization test) and using seven folds cross-validation, which highlighted the similarities among the (methods used in) laboratories. Principal component analysis and hierarchical cluster analysis justified the findings based on SRD ranking/grouping. If the PAH-concentrations are row-scaled, (i.e., z scores are analyzed as input for ranking) SRD can still be used for checking the normality of errors. Moreover, cross-validation of SRD on z scores groups the laboratories similarly. The SRD technique is general in nature, i.e., it can be applied to any experimental problem in which multianalyte results obtained either by several analytical procedures, analysts, instruments, or laboratories need to be compared. [Figure not available: see fulltext.]",
keywords = "Comparison, Comparison of ranks by random numbers, Multianalyte results, Principal component analysis, Sum of ranking differences",
author = "Biljana Škrbić and K. Heberger and {Crossed D Signurišić-Mladenović}, Nataša",
year = "2013",
month = "10",
doi = "10.1007/s00216-013-7206-5",
language = "English",
volume = "405",
pages = "8363--8375",
journal = "Fresenius Zeitschrift fur Analytische Chemie",
issn = "1618-2642",
publisher = "Springer Verlag",
number = "25",

}

TY - JOUR

T1 - Comparison of multianalyte proficiency test results by sum of ranking differences, principal component analysis, and hierarchical cluster analysis

AU - Škrbić, Biljana

AU - Heberger, K.

AU - Crossed D Signurišić-Mladenović, Nataša

PY - 2013/10

Y1 - 2013/10

N2 - Sum of ranking differences (SRD) was applied for comparing multianalyte results obtained by several analytical methods used in one or in different laboratories, i.e., for ranking the overall performances of the methods (or laboratories) in simultaneous determination of the same set of analytes. The data sets for testing of the SRD applicability contained the results reported during one of the proficiency tests (PTs) organized by EU Reference Laboratory for Polycyclic Aromatic Hydrocarbons (EU-RL-PAH). In this way, the SRD was also tested as a discriminant method alternative to existing average performance scores used to compare mutlianalyte PT results. SRD should be used along with the z scores - the most commonly used PT performance statistics. SRD was further developed to handle the same rankings (ties) among laboratories. Two benchmark concentration series were selected as reference: (a) the assigned PAH concentrations (determined precisely beforehand by the EU-RL-PAH) and (b) the averages of all individual PAH concentrations determined by each laboratory. Ranking relative to the assigned values and also to the average (or median) values pointed to the laboratories with the most extreme results, as well as revealed groups of laboratories with similar overall performances. SRD reveals differences between methods or laboratories even if classical test(s) cannot. The ranking was validated using comparison of ranks by random numbers (a randomization test) and using seven folds cross-validation, which highlighted the similarities among the (methods used in) laboratories. Principal component analysis and hierarchical cluster analysis justified the findings based on SRD ranking/grouping. If the PAH-concentrations are row-scaled, (i.e., z scores are analyzed as input for ranking) SRD can still be used for checking the normality of errors. Moreover, cross-validation of SRD on z scores groups the laboratories similarly. The SRD technique is general in nature, i.e., it can be applied to any experimental problem in which multianalyte results obtained either by several analytical procedures, analysts, instruments, or laboratories need to be compared. [Figure not available: see fulltext.]

AB - Sum of ranking differences (SRD) was applied for comparing multianalyte results obtained by several analytical methods used in one or in different laboratories, i.e., for ranking the overall performances of the methods (or laboratories) in simultaneous determination of the same set of analytes. The data sets for testing of the SRD applicability contained the results reported during one of the proficiency tests (PTs) organized by EU Reference Laboratory for Polycyclic Aromatic Hydrocarbons (EU-RL-PAH). In this way, the SRD was also tested as a discriminant method alternative to existing average performance scores used to compare mutlianalyte PT results. SRD should be used along with the z scores - the most commonly used PT performance statistics. SRD was further developed to handle the same rankings (ties) among laboratories. Two benchmark concentration series were selected as reference: (a) the assigned PAH concentrations (determined precisely beforehand by the EU-RL-PAH) and (b) the averages of all individual PAH concentrations determined by each laboratory. Ranking relative to the assigned values and also to the average (or median) values pointed to the laboratories with the most extreme results, as well as revealed groups of laboratories with similar overall performances. SRD reveals differences between methods or laboratories even if classical test(s) cannot. The ranking was validated using comparison of ranks by random numbers (a randomization test) and using seven folds cross-validation, which highlighted the similarities among the (methods used in) laboratories. Principal component analysis and hierarchical cluster analysis justified the findings based on SRD ranking/grouping. If the PAH-concentrations are row-scaled, (i.e., z scores are analyzed as input for ranking) SRD can still be used for checking the normality of errors. Moreover, cross-validation of SRD on z scores groups the laboratories similarly. The SRD technique is general in nature, i.e., it can be applied to any experimental problem in which multianalyte results obtained either by several analytical procedures, analysts, instruments, or laboratories need to be compared. [Figure not available: see fulltext.]

KW - Comparison

KW - Comparison of ranks by random numbers

KW - Multianalyte results

KW - Principal component analysis

KW - Sum of ranking differences

UR - http://www.scopus.com/inward/record.url?scp=84885327124&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885327124&partnerID=8YFLogxK

U2 - 10.1007/s00216-013-7206-5

DO - 10.1007/s00216-013-7206-5

M3 - Article

VL - 405

SP - 8363

EP - 8375

JO - Fresenius Zeitschrift fur Analytische Chemie

JF - Fresenius Zeitschrift fur Analytische Chemie

SN - 1618-2642

IS - 25

ER -