PuSH - Publication Server of Helmholtz Zentrum München

Correcting classifiers for sample selection bias in two-phase case-control studies.

Comput. Math. Methods Med. 2017:7847531 (2017)
Publishers Version Research data DOI
Open Access Gold
Creative Commons Lizenzvertrag
as soon as is submitted to ZB.
Epidemiological studies often utilize stratified data in which rare outcomes or exposures are artificially enriched. This design can increase precision in association tests but distorts predictions when applying classifiers on non-stratified data. Several methods correct for this so-called sample selection bias, but their performance remains unclear especially for machine learning classifiers. With an emphasis on two-phase case-control studies, we aim to assess which corrections to perform in which setting and to obtain methods suitable for machine learning techniques, especially the random forest. We propose two new resampling-based methods to resemble the original data and covariance structure: stochastic inverse-probability oversampling and parametric inverseprobability bagging. We compare all techniques for the random forest and other classifiers, both theoretically and on simulated and real data. Empirical results show that the random forest profits from only the parametric inverse-probability bagging proposed by us. For other classifiers, correction is mostly advantageous, and methods perform uniformly. We discuss consequences of inappropriate distribution assumptions and reason for different ....
Additional Metrics?
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Keywords selection probabilities, stratified sample, bias correction, inverseprobability weights, complex survey design, random forest, logistic regression, decision tree, parametric bootstrap, bagging, machine learning; Prediction Models; Disease; Curves; Design; Size; Men; Sex
Reviewing status