↓ Skip to main content

Bias in random forest variable importance measures: Illustrations, sources and a solution

Overview of attention for article published in BMC Bioinformatics, January 2007
Altmetric Badge

About this Attention Score

  • In the top 5% of all research outputs scored by Altmetric
  • Among the highest-scoring outputs from this source (#40 of 6,520)
  • High Attention Score compared to outputs of the same age (97th percentile)

Mentioned by

blogs
2 blogs
policy
1 policy source
twitter
20 tweeters
googleplus
1 Google+ user
q&a
4 Q&A threads

Citations

dimensions_citation
1587 Dimensions

Readers on

mendeley
1827 Mendeley
citeulike
14 CiteULike
connotea
3 Connotea
You are seeing a free-to-access but limited selection of the activity Altmetric has collected about this research output. Click here to find out more.
Title
Bias in random forest variable importance measures: Illustrations, sources and a solution
Published in
BMC Bioinformatics, January 2007
DOI 10.1186/1471-2105-8-25
Pubmed ID
Authors

Carolin Strobl, Anne-Laure Boulesteix, Achim Zeileis, Torsten Hothorn

Abstract

Variable importance measures for random forests have been receiving increased attention as a means of variable selection in many classification tasks in bioinformatics and related scientific fields, for instance to select a subset of genetic markers relevant for the prediction of a certain disease. We show that random forest variable importance measures are a sensible means for variable selection in many applications, but are not reliable in situations where potential predictor variables vary in their scale of measurement or their number of categories. This is particularly important in genomics and computational biology, where predictors often include variables of different types, for example when predictors include both sequence data and continuous variables such as folding energy, or when amino acid sequence data show different numbers of categories.

Twitter Demographics

The data shown below were collected from the profiles of 20 tweeters who shared this research output. Click here to find out more about how the information was compiled.

Mendeley readers

The data shown below were compiled from readership statistics for 1,827 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
United States 33 2%
Germany 14 <1%
United Kingdom 10 <1%
Canada 7 <1%
Italy 5 <1%
France 4 <1%
Switzerland 3 <1%
Brazil 3 <1%
Belgium 3 <1%
Other 27 1%
Unknown 1718 94%

Demographic breakdown

Readers by professional status Count As %
Student > Ph. D. Student 472 26%
Researcher 342 19%
Student > Master 328 18%
Student > Bachelor 128 7%
Student > Doctoral Student 106 6%
Other 242 13%
Unknown 209 11%
Readers by discipline Count As %
Agricultural and Biological Sciences 308 17%
Computer Science 210 11%
Environmental Science 207 11%
Engineering 164 9%
Earth and Planetary Sciences 91 5%
Other 522 29%
Unknown 325 18%

Attention Score in Context

This research output has an Altmetric Attention Score of 45. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 14 September 2021.
All research outputs
#631,405
of 19,140,651 outputs
Outputs from BMC Bioinformatics
#40
of 6,520 outputs
Outputs of similar age
#2,577
of 102,060 outputs
Outputs of similar age from BMC Bioinformatics
#1
of 1 outputs
Altmetric has tracked 19,140,651 research outputs across all sources so far. Compared to these this one has done particularly well and is in the 96th percentile: it's in the top 5% of all research outputs ever tracked by Altmetric.
So far Altmetric has tracked 6,520 research outputs from this source. They typically receive a little more attention than average, with a mean Attention Score of 5.3. This one has done particularly well, scoring higher than 99% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 102,060 tracked outputs that were published within six weeks on either side of this one in any source. This one has done particularly well, scoring higher than 97% of its contemporaries.
We're also able to compare this research output to 1 others from the same source and published within six weeks on either side of this one. This one has scored higher than all of them