{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T12:27:29Z","timestamp":1781612849458,"version":"3.54.5"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2007,1,25]],"date-time":"2007-01-25T00:00:00Z","timestamp":1169683200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2007,12]]},"DOI":"10.1186\/1471-2105-8-25","type":"journal-article","created":{"date-parts":[[2007,1,25]],"date-time":"2007-01-25T14:13:02Z","timestamp":1169734382000},"source":"Crossref","is-referenced-by-count":2803,"title":["Bias in random forest variable importance measures: Illustrations, sources and a solution"],"prefix":"10.1186","volume":"8","author":[{"given":"Carolin","family":"Strobl","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne-Laure","family":"Boulesteix","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Achim","family":"Zeileis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Torsten","family":"Hothorn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2007,1,25]]},"reference":[{"key":"1397_CR1","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1002\/gepi.20041","volume":"28","author":"A Bureau","year":"2005","unstructured":"Bureau A, Dupuis J, Falls K, Lunetta KL, Hayward B, Keith TP, Eerdewegh PV: Identifying SNPs Predictive of Phenotype Using Random Forests. Genetic Epidemiology 2005, 28: 171\u2013182. 10.1002\/gepi.20041","journal-title":"Genetic Epidemiology"},{"key":"1397_CR2","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/1471-2156-7-23","volume":"7","author":"AG Heidema","year":"2006","unstructured":"Heidema AG, Boer JMA, Nagelkerke N, Mariman ECM, van der A DL, Feskens EJM: The Challenge for Genetic Epidemiologists: How to Analyze Large Numbers of SNPs in Relation to Complex Diseases. BMC Genetics 2006, 7: 23. 10.1186\/1471-2156-7-23","journal-title":"BMC Genetics"},{"key":"1397_CR3","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L: Random Forests. Machine Learning 2001, 45: 5\u201332. 10.1023\/A:1010933404324","journal-title":"Machine Learning"},{"key":"1397_CR4","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/1471-2105-7-3","volume":"7","author":"R D\u00edaz-Uriarte","year":"2006","unstructured":"D\u00edaz-Uriarte R, Alvarez de Andr\u00e9s S: Gene Selection and Classification of Microarray Data Using Random Forest. BMC Bioinformatics 2006, 7: 3. 10.1186\/1471-2105-7-3","journal-title":"BMC Bioinformatics"},{"key":"1397_CR5","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1186\/1471-2156-5-32","volume":"5","author":"KL Lunetta","year":"2004","unstructured":"Lunetta KL, Hayward LB, Segal J, Eerdewegh PV: Screening Large-Scale Association Study Data: Exploiting Interactions Using Random Forests. BMC Genetics 2004, 5: 32. 10.1186\/1471-2156-5-32","journal-title":"BMC Genetics"},{"key":"1397_CR6","doi-asserted-by":"publisher","first-page":"9608","DOI":"10.1073\/pnas.1632587100","volume":"100","author":"EC Gunther","year":"2003","unstructured":"Gunther EC, Stone DJ, Gerwien RW, Bento P, Heyes MP: Prediction of Clinical Drug Efficacy by Classification of Drug-induced Genomic Expression Profiles in vitro . Proceedings of the National Academy of Sciences 2003, 100: 9608\u20139613. 10.1073\/pnas.1632587100","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"1397_CR7","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1186\/1471-2105-6-205","volume":"6","author":"X Huang","year":"2005","unstructured":"Huang X, Pan W, Grindle S, Han X, Chen Y, Park SJ, Miller LW, Hall J: A Comparative Study of Discriminating Human Heart Failure Etiology Using Gene Expression Profiles. BMC Bioinformatics 2005, 6: 205. 10.1186\/1471-2105-6-205","journal-title":"BMC Bioinformatics"},{"key":"1397_CR8","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/modpathol.3800322","volume":"18","author":"Y Shih","year":"2005","unstructured":"Shih Y: Tumor Classification by Tissue Microarray Profiling: Random Forest Clustering Applied to Renal Cell Carcinoma. Modern Pathology 2005, 18: 547\u2013557. 10.1038\/modpathol.3800322","journal-title":"Modern Pathology"},{"key":"1397_CR9","first-page":"2","volume":"3","author":"MR Segal","year":"2004","unstructured":"Segal MR, Barbour JD, Grant RM: Relating HIV-1 Sequence Variation to Replication Capacity via Trees and Forests. Statistical Applications in Genetics and Molecular Biology 2004, 3: 2.","journal-title":"Statistical Applications in Genetics and Molecular Biology"},{"key":"1397_CR10","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1186\/1471-2105-5-137","volume":"5","author":"MP Cummings","year":"2004","unstructured":"Cummings MP, Segal MR: Few Amino Acid Positions in rpoB are Associated with Most of the Rifampin Resistance in Mycobacterium Tuberculosis. BMC Bioinformatics 2004, 5: 137. 10.1186\/1471-2105-5-137","journal-title":"BMC Bioinformatics"},{"key":"1397_CR11","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1186\/1471-2105-5-132","volume":"5","author":"MP Cummings","year":"2004","unstructured":"Cummings MP, Myers DS: Simple Statistical Models Predict C-to-U Edited Sites in Plant Mitochondrial RNA. BMC Bioinformatics 2004, 5: 132. 10.1186\/1471-2105-5-132","journal-title":"BMC Bioinformatics"},{"key":"1397_CR12","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1002\/prot.20865","volume":"63","author":"Y Qi","year":"2006","unstructured":"Qi Y, Bar-Joseph Z, Klein-Seetharaman J: Evaluation of Different Biological Data and Computational Classification Methods for Use in Protein Interaction Prediction. Proteins 2006, 63: 490\u2013500. 10.1002\/prot.20865","journal-title":"Proteins"},{"key":"1397_CR13","doi-asserted-by":"publisher","first-page":"2179","DOI":"10.1021\/ci049849f","volume":"44","author":"R Guha","year":"2003","unstructured":"Guha R, Jurs PC: Development of Linear, Ensemble, and Nonlinear Models for the Prediction and Interpretation of the Biological Activity of a Set of PDGFR Inhibitors. Journal of Chemical Information and Computer Sciences 2003, 44: 2179\u20132189. 10.1021\/ci049849f","journal-title":"Journal of Chemical Information and Computer Sciences"},{"key":"1397_CR14","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1021\/ci034160g","volume":"43","author":"V Svetnik","year":"2003","unstructured":"Svetnik V, Liaw A, Tong C, Culberson JC, Sheridan RP, Feuston BP: Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling. Journal of Chemical Information and Computer Sciences 2003, 43: 1947\u20131958. 10.1021\/ci034160g","journal-title":"Journal of Chemical Information and Computer Sciences"},{"key":"1397_CR15","first-page":"317","volume-title":"Proceedings of the Fourth Asia-Pacific Bioinformatics Conference, Taipei, Taiwan","author":"K Arun","year":"2006","unstructured":"Arun K, Langmead CJ: Structure Based Chemical Shift Prediction Using Random Forests Non-linear Regression. In Proceedings of the Fourth Asia-Pacific Bioinformatics Conference, Taipei, Taiwan Edited by: Jiang T, Yang UC, Chen YPP, Wong L. 2006, 317\u2013326."},{"key":"1397_CR16","volume-title":"Proceedings of the 3rd International Workshop on Distributed Statistical Computing, Vienna, Austria","author":"C Furlanello","year":"2003","unstructured":"Furlanello C, Neteler M, Merler S, Menegon S, Fontanari S, Donini D, Rizzoli A, Chemini C: GIS and the Random Forest Predictor: Integration in R for Tick-Borne Disease Risk Assessment.In Proceedings of the 3rd International Workshop on Distributed Statistical Computing, Vienna, Austria Edited by: Hornik K, Leisch F, Zeileis A. 2003. [\n                    http:\/\/www.ci.tuwien.ac.at\/Conferences\/DSC-2003\/Proceedings\/\n                    \n                  ]"},{"key":"1397_CR17","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1002\/art.21695","volume":"55","author":"MM Ward","year":"2006","unstructured":"Ward MM, Pajevic S, Dreyfuss J, Malley JD: Short-Term Prediction of Mortality in Patients with Systemic Lupus Erythematosus: Classification of Outcomes Using Random Forests. Arthritis and Rheumatism 2006, 55: 74\u201380. 10.1002\/art.21695","journal-title":"Arthritis and Rheumatism"},{"key":"1397_CR18","volume-title":"Classification and Regression Trees","author":"L Breiman","year":"1984","unstructured":"Breiman L, Friedman JH, Olshen RA, Stone CJ: Classification and Regression Trees. New York: Chapman and Hall; 1984."},{"key":"1397_CR19","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"J Friedman","year":"2001","unstructured":"Friedman J: Greedy Function Approximation: A Gradient Boosting Machine. The Annals of Statistics 2001, 29: 1189\u20131232. 10.1214\/aos\/1013203451","journal-title":"The Annals of Statistics"},{"key":"1397_CR20","volume-title":"R: A Language and Environment for Statistical Computing","author":"R Development Core Team","year":"2006","unstructured":"R Development Core Team:R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria; 2006. [\n                    http:\/\/www.R-project.org\/\n                    \n                  ]"},{"key":"1397_CR21","volume-title":"Breiman and Cutler's Random Forests for Classification and Regression","author":"L Breiman","year":"2006","unstructured":"Breiman L, Cutler A, Liaw A, Wiener M:Breiman and Cutler's Random Forests for Classification and Regression. 2006. [R package version 4.5\u201316]. [\n                    http:\/\/CRAN.R-project.org\/\n                    \n                  ] [R package version 4.5\u201316]."},{"key":"1397_CR22","first-page":"18","volume":"2","author":"A Liaw","year":"2002","unstructured":"Liaw A, Wiener M: Classification and Regression by randomForest. R News 2002, 2: 18\u201322. [\n                    http:\/\/CRAN.R-project.org\/doc\/Rnews\/\n                    \n                  ]","journal-title":"R News"},{"key":"1397_CR23","volume-title":"party: A Laboratory for Recursive Part(y)itioning","author":"T Hothorn","year":"2006","unstructured":"Hothorn T, Hornik K, Zeileis A:party: A Laboratory for Recursive Part(y)itioning. 2006. [R package version 0.9\u20130]. [\n                    http:\/\/CRAN.R-project.org\/\n                    \n                  ] [R package version 0.9-0]."},{"key":"1397_CR24","first-page":"1034","volume-title":"Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, Montr\u00e9al, Canada","author":"I Kononenko","year":"1995","unstructured":"Kononenko I: On Biases in Estimating Multi-Valued Attributes. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, Montr\u00e9al, Canada Edited by: Mellish C. 1995, 1034\u20131040."},{"key":"1397_CR25","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1198\/016214501753168271","volume":"96","author":"H Kim","year":"2001","unstructured":"Kim H, Loh W: Classification Trees with Unbiased Multiway Splits. Journal of the American Statistical Association 2001, 96: 589\u2013604. 10.1198\/016214501753168271","journal-title":"Journal of the American Statistical Association"},{"key":"1397_CR26","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1002\/bimj.200510161","volume":"48","author":"AL Boulesteix","year":"2006","unstructured":"Boulesteix AL: Maximally Selected Chi-square Statistics for Ordinal Variables. Biometrical Journal 2006, 48: 451\u2013462. 10.1002\/bimj.200510161","journal-title":"Biometrical Journal"},{"key":"1397_CR27","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1002\/bimj.200510191","volume":"48","author":"AL Boulesteix","year":"2006","unstructured":"Boulesteix AL: Maximally Selected Chi-square Statistics and Binary Splits of Nominal Variables. Biometrical Journal 2006, 48: 838\u2013848. 10.1002\/bimj.200510191","journal-title":"Biometrical Journal"},{"key":"1397_CR28","volume-title":"Computational Statistics & Data Analysis","author":"C Strobl","year":"2006","unstructured":"Strobl C, Boulesteix AL, Augustin T: Unbiased Split Selection for Classification Trees Based on the Gini Index. Computational Statistics & Data Analysis 2006. [\n                    http:\/\/dx.doi.org\/10.1016\/j.csda.2006.12.030\n                    \n                  ]"},{"key":"1397_CR29","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1198\/106186006X133933","volume":"15","author":"T Hothorn","year":"2006","unstructured":"Hothorn T, Hornik K, Zeileis A: Unbiased Recursive Partitioning: A Conditional Inference Framework. Journal of Computational and Graphical Statistics 2006, 15: 651\u2013674. 10.1198\/106186006X133933","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"1397_CR30","volume-title":"preprint","author":"J Friedman","year":"1999","unstructured":"Friedman J, Hall P: On Bagging and Nonlinear Estimation. preprint 1999. [\n                    http:\/\/www-stat.stanford.edu\/~jhf\/\n                    \n                  ]"},{"key":"1397_CR31","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1214\/aos\/1031689014","volume":"30","author":"P B\u00fchlmann","year":"2002","unstructured":"B\u00fchlmann P, Yu B: Analyzing Bagging. The Annals of Statistics 2002, 30: 927\u2013961. 10.1214\/aos\/1031689014","journal-title":"The Annals of Statistics"},{"key":"1397_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1554-7","volume-title":"Subsampling","author":"DN Politis","year":"1999","unstructured":"Politis DN, Romano JP, Wolf M: Subsampling. New York: Springer; 1999."},{"key":"1397_CR33","first-page":"90","volume-title":"Proceedings of the Seventeenth International Conference on Machine Learning, Williams College, Williamstown, MA, USA","author":"A Dobra","year":"2001","unstructured":"Dobra A, Gehrke J: Bias Correction in Classification Tree Construction. In Proceedings of the Seventeenth International Conference on Machine Learning, Williams College, Williamstown, MA, USA Edited by: Brodley CE, Danyluk AP. 2001, 90\u201397."},{"key":"1397_CR34","volume-title":"Discussion Paper 420, SFB \"Statistical Analysis of Discrete Structures\", Munich, Germany","author":"C Strobl","year":"2005","unstructured":"Strobl C: Statistical Sources of Variable Selection Bias in Classification Tree Algorithms Based on the Gini Index. Discussion Paper 420, SFB \"Statistical Analysis of Discrete Structures\", Munich, Germany 2005. [\n                    http:\/\/www.stat.uni-muenchen.de\/sfb386\/papers\/dsp\/paper420.ps\n                    \n                  ]"},{"key":"1397_CR35","first-page":"340","volume-title":"Proceedings of the Fourth International Symposium on Imprecise Probabilities and Their Applications, Carnegy Mellon University, Pittsburgh, PA, USA","author":"C Strobl","year":"2005","unstructured":"Strobl C: Variable Selection in Classification Trees Based on Imprecise Probabilities. In Proceedings of the Fourth International Symposium on Imprecise Probabilities and Their Applications, Carnegy Mellon University, Pittsburgh, PA, USA Edited by: Cozman F, Nau R, Seidenfeld T. 2005, 340\u2013348."},{"key":"1397_CR36","volume-title":"rpart: Recursive Partitioning","author":"TM Therneau","year":"2006","unstructured":"Therneau TM, Atkinson B, Ripley BD:rpart: Recursive Partitioning. 2006. [R package version 3.1\u201330]. [\n                    http:\/\/CRAN.R-project.org\/\n                    \n                  ] [R package version 3.1\u201330]."},{"key":"1397_CR37","first-page":"91","volume-title":"State of the Art in Probability and Statistics, Festschrift for Willem R. van Zwet, IMS Lecture Notes Monograph Series, Beachwood, OH, USA","author":"PJ Bickel","year":"2001","unstructured":"Bickel PJ, Ren JJ: The Bootstrap in Hypothesis Testing. In State of the Art in Probability and Statistics, Festschrift for Willem R. van Zwet, IMS Lecture Notes Monograph Series, Beachwood, OH, USA Edited by: de Gunst M, Klaassen C, van der Vaart A. 2001, 36: 91\u2013112."},{"key":"1397_CR38","first-page":"1008","volume":"2","author":"M van der Laan","year":"2006","unstructured":"van der Laan M: Statistical Inference for Variable Importance. International Journal of Biostatistics 2006, 2: 1008\u20131008.","journal-title":"International Journal of Biostatistics"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-8-25.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1471-2105-8-25\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-8-25.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,23]],"date-time":"2019-01-23T04:05:45Z","timestamp":1548216345000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/1471-2105-8-25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,1,25]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2007,12]]}},"alternative-id":["1397"],"URL":"https:\/\/doi.org\/10.1186\/1471-2105-8-25","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007,1,25]]},"article-number":"25"}}