Tests of association under misclassification: Application to histological sampling in oncology

Rebecca Betensky, David N. Louis, J. Gregory Cairncross

Research output: Contribution to journalArticle

Abstract

Subjects in tumour studies are often misclassified with respect to histologic features that are not routinely recorded in diagnostic reports and that display heterogeneity within tumours. Pathologic analysis of the tumours may miss the feature of interest if the pathologist was not alerted to detail the microscopic feature of interest or if it is not present in the selected specimens. In this setting, only the subjects for whom the outcome is not found are potentially misclassified. Analyses of associations between the observed, potentially misclassified, outcome and a second outcome are invalid if the probability of misclassification depends on the second outcome. Three natural tests of association based on the observed data depend on different numbers of nuisance parameters. Most promising is a test based on the ratio of proportions of the observed feature. We illustrate this test using a study of the association of imaging parameters with genetic features in subjects with oligodendroglioma, a common brain tumour. In this study, calcification, a feature related to the imaging parameters, was potentially misclassified as not present.

Original languageEnglish (US)
Pages (from-to)4808-4816
Number of pages9
JournalStatistics in Medicine
Volume26
Issue number26
DOIs
StatePublished - Nov 20 2007

Fingerprint

Oncology
Misclassification
Tumor
Oligodendroglioma
Neoplasms
Imaging
Probability of Misclassification
Brain Tumor
Brain Neoplasms
Nuisance Parameter
Display
Diagnostics
Proportion

Keywords

  • Confidence set p-value
  • Nuisance parameters

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Tests of association under misclassification : Application to histological sampling in oncology. / Betensky, Rebecca; Louis, David N.; Cairncross, J. Gregory.

In: Statistics in Medicine, Vol. 26, No. 26, 20.11.2007, p. 4808-4816.

Research output: Contribution to journalArticle

Betensky, Rebecca ; Louis, David N. ; Cairncross, J. Gregory. / Tests of association under misclassification : Application to histological sampling in oncology. In: Statistics in Medicine. 2007 ; Vol. 26, No. 26. pp. 4808-4816.
@article{2c96a47d6178440e905bce7a5c43cc0f,
title = "Tests of association under misclassification: Application to histological sampling in oncology",
abstract = "Subjects in tumour studies are often misclassified with respect to histologic features that are not routinely recorded in diagnostic reports and that display heterogeneity within tumours. Pathologic analysis of the tumours may miss the feature of interest if the pathologist was not alerted to detail the microscopic feature of interest or if it is not present in the selected specimens. In this setting, only the subjects for whom the outcome is not found are potentially misclassified. Analyses of associations between the observed, potentially misclassified, outcome and a second outcome are invalid if the probability of misclassification depends on the second outcome. Three natural tests of association based on the observed data depend on different numbers of nuisance parameters. Most promising is a test based on the ratio of proportions of the observed feature. We illustrate this test using a study of the association of imaging parameters with genetic features in subjects with oligodendroglioma, a common brain tumour. In this study, calcification, a feature related to the imaging parameters, was potentially misclassified as not present.",
keywords = "Confidence set p-value, Nuisance parameters",
author = "Rebecca Betensky and Louis, {David N.} and Cairncross, {J. Gregory}",
year = "2007",
month = "11",
day = "20",
doi = "10.1002/sim.2895",
language = "English (US)",
volume = "26",
pages = "4808--4816",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "26",

}

TY - JOUR

T1 - Tests of association under misclassification

T2 - Application to histological sampling in oncology

AU - Betensky, Rebecca

AU - Louis, David N.

AU - Cairncross, J. Gregory

PY - 2007/11/20

Y1 - 2007/11/20

N2 - Subjects in tumour studies are often misclassified with respect to histologic features that are not routinely recorded in diagnostic reports and that display heterogeneity within tumours. Pathologic analysis of the tumours may miss the feature of interest if the pathologist was not alerted to detail the microscopic feature of interest or if it is not present in the selected specimens. In this setting, only the subjects for whom the outcome is not found are potentially misclassified. Analyses of associations between the observed, potentially misclassified, outcome and a second outcome are invalid if the probability of misclassification depends on the second outcome. Three natural tests of association based on the observed data depend on different numbers of nuisance parameters. Most promising is a test based on the ratio of proportions of the observed feature. We illustrate this test using a study of the association of imaging parameters with genetic features in subjects with oligodendroglioma, a common brain tumour. In this study, calcification, a feature related to the imaging parameters, was potentially misclassified as not present.

AB - Subjects in tumour studies are often misclassified with respect to histologic features that are not routinely recorded in diagnostic reports and that display heterogeneity within tumours. Pathologic analysis of the tumours may miss the feature of interest if the pathologist was not alerted to detail the microscopic feature of interest or if it is not present in the selected specimens. In this setting, only the subjects for whom the outcome is not found are potentially misclassified. Analyses of associations between the observed, potentially misclassified, outcome and a second outcome are invalid if the probability of misclassification depends on the second outcome. Three natural tests of association based on the observed data depend on different numbers of nuisance parameters. Most promising is a test based on the ratio of proportions of the observed feature. We illustrate this test using a study of the association of imaging parameters with genetic features in subjects with oligodendroglioma, a common brain tumour. In this study, calcification, a feature related to the imaging parameters, was potentially misclassified as not present.

KW - Confidence set p-value

KW - Nuisance parameters

UR - http://www.scopus.com/inward/record.url?scp=35648981567&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35648981567&partnerID=8YFLogxK

U2 - 10.1002/sim.2895

DO - 10.1002/sim.2895

M3 - Article

C2 - 17476651

AN - SCOPUS:35648981567

VL - 26

SP - 4808

EP - 4816

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 26

ER -