Comparing the areas under two correlated ROC curves : Parametric and non- parametric approaches
Identifieur interne : 001174 ( Main/Exploration ); précédent : 001173; suivant : 001175Comparing the areas under two correlated ROC curves : Parametric and non- parametric approaches
Auteurs : Katy Molodianovitch [Israël] ; David Faraggi [Israël] ; Benjamin Reiser [Israël]Source :
- Biometrical journal [ 0323-3847 ] ; 2006.
Descripteurs français
- Pascal (Inist)
- Analyse corrélation, Méthode ROC, Test non paramétrique, Test paramétrique, Méthode statistique, Puissance test, Simulation statistique, Biométrie, Science vie, Superficie, Caractéristique, Caractéristiques, Statistique, Analyse statistique, Boîte, Modèle Cox, Procédure, Méthodologie, OCR, Courbe paramétrique, Terme, Normalité, Courbe Roc, Test Cox, Transformation puissance, Niveau signification.
- Wicri :
- topic : Méthode statistique, Biométrie, Statistique.
English descriptors
- KwdEn :
- Area, Biometrics, Box, Characteristic, Characteristics, Correlation analysis, Cox model, Cox test, Life science, Methodology, Non parametric test, Parametric test, Power transformation, Procedure, Receiver operating characteristic curves, Roc curve, Significance level, Statistical analysis, Statistical method, Statistical simulation, Statistics, Test power.
Abstract
In order to compare the discriminatory effectiveness of two diagnostic markers the equality of the areas under the respective Receiver Operating Characteristic Curves is commonly tested. A non-parametric test based on the Mann-Whitney statistic is generally used. Weiand et al. (1989) present a parametric test based on normal distributional assumptions. We extend this test using the Box-Cox power family of transformations to non-normal situations. These three test procedures are compared in terms of significance level and power by means of a large simulation study. Overall we find that transforming to normality is to be preferred. An example of two pancreatic cancer serum biomarkers is used to illustrate the methodology.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000363
- to stream PascalFrancis, to step Curation: 000423
- to stream PascalFrancis, to step Checkpoint: 000344
- to stream Main, to step Merge: 001205
- to stream Main, to step Curation: 001174
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Comparing the areas under two correlated ROC curves : Parametric and non- parametric approaches</title><author><name sortKey="Molodianovitch, Katy" sort="Molodianovitch, Katy" uniqKey="Molodianovitch K" first="Katy" last="Molodianovitch">Katy Molodianovitch</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Statistics, University of Haifa</s1><s2>31905</s2><s3>ISR</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Israël</country><wicri:noRegion>31905</wicri:noRegion></affiliation></author><author><name sortKey="Faraggi, David" sort="Faraggi, David" uniqKey="Faraggi D" first="David" last="Faraggi">David Faraggi</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Statistics, University of Haifa</s1><s2>31905</s2><s3>ISR</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Israël</country><wicri:noRegion>31905</wicri:noRegion></affiliation></author><author><name sortKey="Reiser, Benjamin" sort="Reiser, Benjamin" uniqKey="Reiser B" first="Benjamin" last="Reiser">Benjamin Reiser</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Statistics, University of Haifa</s1><s2>31905</s2><s3>ISR</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Israël</country><wicri:noRegion>31905</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">06-0500462</idno><date when="2006">2006</date><idno type="stanalyst">PASCAL 06-0500462 INIST</idno><idno type="RBID">Pascal:06-0500462</idno><idno type="wicri:Area/PascalFrancis/Corpus">000363</idno><idno type="wicri:Area/PascalFrancis/Curation">000423</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000344</idno><idno type="wicri:doubleKey">0323-3847:2006:Molodianovitch K:comparing:the:areas</idno><idno type="wicri:Area/Main/Merge">001205</idno><idno type="wicri:Area/Main/Curation">001174</idno><idno type="wicri:Area/Main/Exploration">001174</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Comparing the areas under two correlated ROC curves : Parametric and non- parametric approaches</title><author><name sortKey="Molodianovitch, Katy" sort="Molodianovitch, Katy" uniqKey="Molodianovitch K" first="Katy" last="Molodianovitch">Katy Molodianovitch</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Statistics, University of Haifa</s1><s2>31905</s2><s3>ISR</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Israël</country><wicri:noRegion>31905</wicri:noRegion></affiliation></author><author><name sortKey="Faraggi, David" sort="Faraggi, David" uniqKey="Faraggi D" first="David" last="Faraggi">David Faraggi</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Statistics, University of Haifa</s1><s2>31905</s2><s3>ISR</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Israël</country><wicri:noRegion>31905</wicri:noRegion></affiliation></author><author><name sortKey="Reiser, Benjamin" sort="Reiser, Benjamin" uniqKey="Reiser B" first="Benjamin" last="Reiser">Benjamin Reiser</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Statistics, University of Haifa</s1><s2>31905</s2><s3>ISR</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Israël</country><wicri:noRegion>31905</wicri:noRegion></affiliation></author></analytic><series><title level="j" type="main">Biometrical journal</title><title level="j" type="abbreviated">Biom. j.</title><idno type="ISSN">0323-3847</idno><imprint><date when="2006">2006</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Biometrical journal</title><title level="j" type="abbreviated">Biom. j.</title><idno type="ISSN">0323-3847</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Area</term><term>Biometrics</term><term>Box</term><term>Characteristic</term><term>Characteristics</term><term>Correlation analysis</term><term>Cox model</term><term>Cox test</term><term>Life science</term><term>Methodology</term><term>Non parametric test</term><term>Parametric test</term><term>Power transformation</term><term>Procedure</term><term>Receiver operating characteristic curves</term><term>Roc curve</term><term>Significance level</term><term>Statistical analysis</term><term>Statistical method</term><term>Statistical simulation</term><term>Statistics</term><term>Test power</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Analyse corrélation</term><term>Méthode ROC</term><term>Test non paramétrique</term><term>Test paramétrique</term><term>Méthode statistique</term><term>Puissance test</term><term>Simulation statistique</term><term>Biométrie</term><term>Science vie</term><term>Superficie</term><term>Caractéristique</term><term>Caractéristiques</term><term>Statistique</term><term>Analyse statistique</term><term>Boîte</term><term>Modèle Cox</term><term>Procédure</term><term>Méthodologie</term><term>OCR</term><term>Courbe paramétrique</term><term>Terme</term><term>Normalité</term><term>Courbe Roc</term><term>Test Cox</term><term>Transformation puissance</term><term>Niveau signification</term></keywords><keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Méthode statistique</term><term>Biométrie</term><term>Statistique</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">In order to compare the discriminatory effectiveness of two diagnostic markers the equality of the areas under the respective Receiver Operating Characteristic Curves is commonly tested. A non-parametric test based on the Mann-Whitney statistic is generally used. Weiand et al. (1989) present a parametric test based on normal distributional assumptions. We extend this test using the Box-Cox power family of transformations to non-normal situations. These three test procedures are compared in terms of significance level and power by means of a large simulation study. Overall we find that transforming to normality is to be preferred. An example of two pancreatic cancer serum biomarkers is used to illustrate the methodology.</div></front></TEI><affiliations><list><country><li>Israël</li></country></list><tree><country name="Israël"><noRegion><name sortKey="Molodianovitch, Katy" sort="Molodianovitch, Katy" uniqKey="Molodianovitch K" first="Katy" last="Molodianovitch">Katy Molodianovitch</name></noRegion><name sortKey="Faraggi, David" sort="Faraggi, David" uniqKey="Faraggi D" first="David" last="Faraggi">David Faraggi</name><name sortKey="Reiser, Benjamin" sort="Reiser, Benjamin" uniqKey="Reiser B" first="Benjamin" last="Reiser">Benjamin Reiser</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001174 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001174 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= Pascal:06-0500462
|texte= Comparing the areas under two correlated ROC curves : Parametric and non- parametric approaches
}}
| This area was generated with Dilib version V0.6.32. |  |