Influence Measures for CART Classification Trees

@article{BarHen2015InfluenceMF,
  title={Influence Measures for CART Classification Trees},
  author={Avner Bar-Hen and Servane Gey and Jean-Michel Poggi},
  journal={J. Classification},
  year={2015},
  volume={32},
  pages={21-45}
}
This paper deals with measuring the influence of observations on the results obtained with CART classification trees. To define the influence of individuals on the analysis, we use influence functions to propose some general criterions to measure the sensitivity of the CART analysis and its robustness. The proposals, based on jakknife trees, are organized around two lines: influence on predictions and influence on partitions. In addition, the analysis is extended to the pruned sequences of CART… CONTINUE READING

From This Paper

Topics from this paper.
3 Citations
22 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 22 references

Outlier detection by boosting regression trees

  • N. Chèze, J. M. Poggi
  • Journal of Statistical Research of Iran (JSRI),
  • 2006
Highly Influential
6 Excerpts

Recursive Partitioning and Applications, 2nd edition, Springer

  • H. Zhang, B. H. Singer
  • Val de Marne Haut de Seine Seine Saint Denis…
  • 2010
2 Excerpts

Similar Papers

Loading similar papers…