nonbinROC: Software for Evaluating Diagnostic Accuracies with Non-Binary Gold Standards

ROC analysis is a standard method for estimating and comparing diagnostic tests' accuracies when the gold standard is binary. However, there are many situations when the gold standard is not binary. In these situations, traditional ROC methods applied have lead to biased and uninformative outco...

Full description

Bibliographic Details
Main Author: Paul Nguyen
Format: Article
Language:English
Published: Foundation for Open Access Statistics 2007-09-01
Series:Journal of Statistical Software
Subjects:
Online Access:http://www.jstatsoft.org/v21/i10/paper
_version_ 1811255620365451264
author Paul Nguyen
author_facet Paul Nguyen
author_sort Paul Nguyen
collection DOAJ
description ROC analysis is a standard method for estimating and comparing diagnostic tests' accuracies when the gold standard is binary. However, there are many situations when the gold standard is not binary. In these situations, traditional ROC methods applied have lead to biased and uninformative outcomes. This article introduces nonbinROC, software for R that implements nonparametric estimators proposed by Obuchowski (2005) for estimating and comparing diagnostic tests' accuracies when the gold standard is measured on a continuous, ordinal or nominal scale. The results produced from these estimators are interpreted in the same manner as in ROC analysis but are not associated with any ROC curve.
first_indexed 2024-04-12T17:26:41Z
format Article
id doaj.art-c351f72bdc934ca3b387aab5d92b655d
institution Directory Open Access Journal
issn 1548-7660
language English
last_indexed 2024-04-12T17:26:41Z
publishDate 2007-09-01
publisher Foundation for Open Access Statistics
record_format Article
series Journal of Statistical Software
spelling doaj.art-c351f72bdc934ca3b387aab5d92b655d2022-12-22T03:23:16ZengFoundation for Open Access StatisticsJournal of Statistical Software1548-76602007-09-012110nonbinROC: Software for Evaluating Diagnostic Accuracies with Non-Binary Gold StandardsPaul NguyenROC analysis is a standard method for estimating and comparing diagnostic tests' accuracies when the gold standard is binary. However, there are many situations when the gold standard is not binary. In these situations, traditional ROC methods applied have lead to biased and uninformative outcomes. This article introduces nonbinROC, software for R that implements nonparametric estimators proposed by Obuchowski (2005) for estimating and comparing diagnostic tests' accuracies when the gold standard is measured on a continuous, ordinal or nominal scale. The results produced from these estimators are interpreted in the same manner as in ROC analysis but are not associated with any ROC curve.http://www.jstatsoft.org/v21/i10/paperROCgold standarddiagnostic testcontinuous scaleordinal scalenominal scale
spellingShingle Paul Nguyen
nonbinROC: Software for Evaluating Diagnostic Accuracies with Non-Binary Gold Standards
Journal of Statistical Software
ROC
gold standard
diagnostic test
continuous scale
ordinal scale
nominal scale
title nonbinROC: Software for Evaluating Diagnostic Accuracies with Non-Binary Gold Standards
title_full nonbinROC: Software for Evaluating Diagnostic Accuracies with Non-Binary Gold Standards
title_fullStr nonbinROC: Software for Evaluating Diagnostic Accuracies with Non-Binary Gold Standards
title_full_unstemmed nonbinROC: Software for Evaluating Diagnostic Accuracies with Non-Binary Gold Standards
title_short nonbinROC: Software for Evaluating Diagnostic Accuracies with Non-Binary Gold Standards
title_sort nonbinroc software for evaluating diagnostic accuracies with non binary gold standards
topic ROC
gold standard
diagnostic test
continuous scale
ordinal scale
nominal scale
url http://www.jstatsoft.org/v21/i10/paper
work_keys_str_mv AT paulnguyen nonbinrocsoftwareforevaluatingdiagnosticaccuracieswithnonbinarygoldstandards