Nonparametric estimation of the cumulative incidence function under outcome misclassification using external validation data

Jessie K. Edwards, Giorgos Bakoyannis, Constantin T. Yiannoutsos, Margaret W. Mburu, Stephen R. Cole

Research output: Contribution to journalArticle

Abstract

Misclassification of outcomes or event types is common in health sciences research and can lead to serious bias when estimating the cumulative incidence functions in settings with competing risks. Recent work has shown how to estimate nonparametric cumulative incidence functions in the presence of nondifferential outcome misclassification when the misclassification probabilities are known. Here, we extend this approach to account for misclassification that is differential with respect to important predictors of the outcome using misclassification probabilities estimated from external validation data. Moreover, we propose a bootstrap approach in which the observations from both the main study data and the external validation study are resampled to allow the uncertainty in the misclassification probabilities to propagate through the analysis into the final confidence intervals, ensuring appropriate confidence interval coverage probabilities. The proposed estimator is shown to be uniformly consistent and simulation studies indicate that both the estimator and the standard error estimation approach perform well in finite samples. The methodology is applied to estimate the cumulative incidence of death and disengagement from HIV care in a large cohort of HIV infected individuals in sub-Saharan Africa, where a significant death underreporting issue leads to outcome misclassification. This analysis uses external validation data from a separate study conducted in the same country.

Original languageEnglish (US)
Pages (from-to)5512-5527
Number of pages16
JournalStatistics in Medicine
Volume38
Issue number29
DOIs
StatePublished - Dec 20 2019
Externally publishedYes

Fingerprint

Cumulative Incidence Function
Misclassification
Misclassification Probability
Nonparametric Estimation
Incidence
Confidence interval
HIV
Confidence Intervals
Interval Probability
Estimator
Competing Risks
Africa South of the Sahara
Validation Studies
Coverage Probability
Error Estimation
Standard error
Estimate
Bootstrap
Uncertainty
Predictors

Keywords

  • competing risks
  • cumulative incidence
  • external validation data
  • misclassification

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Nonparametric estimation of the cumulative incidence function under outcome misclassification using external validation data. / Edwards, Jessie K.; Bakoyannis, Giorgos; Yiannoutsos, Constantin T.; Mburu, Margaret W.; Cole, Stephen R.

In: Statistics in Medicine, Vol. 38, No. 29, 20.12.2019, p. 5512-5527.

Research output: Contribution to journalArticle

@article{d717f158bbf24f0bb2099bb440511042,
title = "Nonparametric estimation of the cumulative incidence function under outcome misclassification using external validation data",
abstract = "Misclassification of outcomes or event types is common in health sciences research and can lead to serious bias when estimating the cumulative incidence functions in settings with competing risks. Recent work has shown how to estimate nonparametric cumulative incidence functions in the presence of nondifferential outcome misclassification when the misclassification probabilities are known. Here, we extend this approach to account for misclassification that is differential with respect to important predictors of the outcome using misclassification probabilities estimated from external validation data. Moreover, we propose a bootstrap approach in which the observations from both the main study data and the external validation study are resampled to allow the uncertainty in the misclassification probabilities to propagate through the analysis into the final confidence intervals, ensuring appropriate confidence interval coverage probabilities. The proposed estimator is shown to be uniformly consistent and simulation studies indicate that both the estimator and the standard error estimation approach perform well in finite samples. The methodology is applied to estimate the cumulative incidence of death and disengagement from HIV care in a large cohort of HIV infected individuals in sub-Saharan Africa, where a significant death underreporting issue leads to outcome misclassification. This analysis uses external validation data from a separate study conducted in the same country.",
keywords = "competing risks, cumulative incidence, external validation data, misclassification",
author = "Edwards, {Jessie K.} and Giorgos Bakoyannis and Yiannoutsos, {Constantin T.} and Mburu, {Margaret W.} and Cole, {Stephen R.}",
year = "2019",
month = "12",
day = "20",
doi = "10.1002/sim.8380",
language = "English (US)",
volume = "38",
pages = "5512--5527",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "29",

}

TY - JOUR

T1 - Nonparametric estimation of the cumulative incidence function under outcome misclassification using external validation data

AU - Edwards, Jessie K.

AU - Bakoyannis, Giorgos

AU - Yiannoutsos, Constantin T.

AU - Mburu, Margaret W.

AU - Cole, Stephen R.

PY - 2019/12/20

Y1 - 2019/12/20

N2 - Misclassification of outcomes or event types is common in health sciences research and can lead to serious bias when estimating the cumulative incidence functions in settings with competing risks. Recent work has shown how to estimate nonparametric cumulative incidence functions in the presence of nondifferential outcome misclassification when the misclassification probabilities are known. Here, we extend this approach to account for misclassification that is differential with respect to important predictors of the outcome using misclassification probabilities estimated from external validation data. Moreover, we propose a bootstrap approach in which the observations from both the main study data and the external validation study are resampled to allow the uncertainty in the misclassification probabilities to propagate through the analysis into the final confidence intervals, ensuring appropriate confidence interval coverage probabilities. The proposed estimator is shown to be uniformly consistent and simulation studies indicate that both the estimator and the standard error estimation approach perform well in finite samples. The methodology is applied to estimate the cumulative incidence of death and disengagement from HIV care in a large cohort of HIV infected individuals in sub-Saharan Africa, where a significant death underreporting issue leads to outcome misclassification. This analysis uses external validation data from a separate study conducted in the same country.

AB - Misclassification of outcomes or event types is common in health sciences research and can lead to serious bias when estimating the cumulative incidence functions in settings with competing risks. Recent work has shown how to estimate nonparametric cumulative incidence functions in the presence of nondifferential outcome misclassification when the misclassification probabilities are known. Here, we extend this approach to account for misclassification that is differential with respect to important predictors of the outcome using misclassification probabilities estimated from external validation data. Moreover, we propose a bootstrap approach in which the observations from both the main study data and the external validation study are resampled to allow the uncertainty in the misclassification probabilities to propagate through the analysis into the final confidence intervals, ensuring appropriate confidence interval coverage probabilities. The proposed estimator is shown to be uniformly consistent and simulation studies indicate that both the estimator and the standard error estimation approach perform well in finite samples. The methodology is applied to estimate the cumulative incidence of death and disengagement from HIV care in a large cohort of HIV infected individuals in sub-Saharan Africa, where a significant death underreporting issue leads to outcome misclassification. This analysis uses external validation data from a separate study conducted in the same country.

KW - competing risks

KW - cumulative incidence

KW - external validation data

KW - misclassification

UR - http://www.scopus.com/inward/record.url?scp=85074557391&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074557391&partnerID=8YFLogxK

U2 - 10.1002/sim.8380

DO - 10.1002/sim.8380

M3 - Article

C2 - 31647581

AN - SCOPUS:85074557391

VL - 38

SP - 5512

EP - 5527

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 29

ER -