ML Anthology

Tree-Structured Model Diagnostics for Linear Regression

Xiaogang Su, Chih-Ling Tsai, Morgan C. Wang
MLJ 2009 pp. 111-131
doi:10.1007/S10994-008-5080-8 /mlj/2009/su2009mlj-treestructured/

Abstract

This paper studies model diagnostics for linear regression models. We propose two tree-based procedures to check the adequacy of linear functional form and the appropriateness of homoscedasticity, respectively. The proposed tree methods not only facilitate a natural assessment of the linear model, but also automatically provide clues for amending deficiencies. We explore and illustrate their uses via both Monte Carlo studies and real data examples.

PDF MLJ Semantic Scholar

Cite

Text

Su et al. "Tree-Structured Model Diagnostics for Linear Regression." Machine Learning, 2009. doi:10.1007/S10994-008-5080-8

Markdown

[Su et al. "Tree-Structured Model Diagnostics for Linear Regression." Machine Learning, 2009.](https://mlanthology.org/mlj/2009/su2009mlj-treestructured/) doi:10.1007/S10994-008-5080-8

BibTeX

@article{su2009mlj-treestructured,
  title     = {{Tree-Structured Model Diagnostics for Linear Regression}},
  author    = {Su, Xiaogang and Tsai, Chih-Ling and Wang, Morgan C.},
  journal   = {Machine Learning},
  year      = {2009},
  pages     = {111-131},
  doi       = {10.1007/S10994-008-5080-8},
  volume    = {74},
  url       = {https://mlanthology.org/mlj/2009/su2009mlj-treestructured/}
}