Conditional variable importance for random forests - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2008 Jul 11:9:307.
doi: 10.1186/1471-2105-9-307.

Conditional variable importance for random forests

Carolin Strobl  1 , Anne-Laure Boulesteix, Thomas Kneib, Thomas Augustin, Achim Zeileis
Affiliations

Conditional variable importance for random forests

Carolin Strobl et al. BMC Bioinformatics. .

Abstract

Background: Random forests are becoming increasingly popular in many scientific fields because they can cope with "small n large p" problems, complex interactions and even highly correlated predictor variables. Their variable importance measures have recently been suggested as screening tools for, e.g., gene expression studies. However, these variable importance measures show a bias towards correlated predictor variables.

Results: We identify two mechanisms responsible for this finding: (i) A preference for the selection of correlated predictors in the tree building process and (ii) an additional advantage for correlated predictor variables induced by the unconditional permutation scheme that is employed in the computation of the variable importance measure. Based on these considerations we develop a new, conditional permutation scheme for the computation of the variable importance measure.

Conclusion: The resulting conditional variable importance reflects the true impact of each predictor variable more reliably than the original marginal approach.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Selection rates. Relative selection rates for twelve variables in the first splits (left) and in all splits (right) of all trees in random forests built with different values for mtry.
Figure 2
Figure 2
Permutation scheme for the original marginal (left) and for the newly suggested conditional (right) permutation importance.
Figure 3
Figure 3
Permutation importance. Median permutation importance for marginal (dashed) and conditional (solid) permutation scheme along with inter-quartile range. Note that the ordering of variables in the plot is arbitrary.
Figure 4
Figure 4
Example: peptide-binding data. Marginal (top) and conditional (bottom) permutation importance of 104 predictors of peptide-binding.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Breiman L. Random Forests. Machine Learning. 2001;45:5–32. doi: 10.1023/A:1010933404324. - DOI
    1. Lunetta KL, Hayward LB, Segal J, Eerdewegh PV. Screening Large-Scale Association Study Data: Exploiting Interactions Using Random Forests. BMC Genetics. 2004;5:32. doi: 10.1186/1471-2156-5-32. - DOI - PMC - PubMed
    1. 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;28:171–182. doi: 10.1002/gepi.20041. - DOI - PubMed
    1. 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. doi: 10.1186/1471-2105-6-205. - DOI - PMC - PubMed
    1. 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;63:490–500. doi: 10.1002/prot.20865. - DOI - PMC - PubMed

Publication types

LinkOut - more resources