Evaluating Microarray-based Classifiers: An Overview
Anne‐Laure Boulesteix, Carolin Strobl, Thomas Augustin et al. · Cancer Informatics · 2008
For the last eight years, microarray-based class prediction has been the subject of numerous publications in medicine, bioinformatics and statistics journals. However, in many articles, the assessment of classification accuracy is carried out using suboptimal procedures and is not paid much attention. In this paper, we carefully review various statistical aspects of classifier evaluation and validation from a practical point of view. The main topics addressed are accuracy measures, error rate estimation procedures, variable selection, choice of classifiers and validation strategy.
Cited by 114 works. doi:10.4137/cin.s408 Open-access PDF
Authors
References
- R: A Language and Environment for Statistical Computing
- The Nature of Statistical Learning Theory
- Genetic algorithms in search, optimization, and machine learning
- Random Forests
- The meaning and use of the area under a receiver operating characteristic (ROC) curve.
- Bagging Predictors
- Journal of The American Statistical Association
- A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
- Genetic Algorithms in Search, Optimization and Machine Learning
- The Elements of Statistical Learning