Open Access
Translator Disclaimer
May 2016 Identifying Outlying Observations in Regression Trees
Nicholas Granered, Samantha C. Bates Prins
Missouri J. Math. Sci. 28(1): 76-87 (May 2016). DOI: 10.35834/mjms/1474295357


Regression trees are an alternative to classical linear regression models that seek to fit a piecewise linear model to data. The structure of regression trees makes them well-suited to the modeling of data containing outliers. We propose an algorithm that takes advantage of this feature in order to automatically detect outliers. This new algorithm performs well on the four test datasets [7] that are considered to be necessary for a valid outlier detection algorithm in a linear regression context, even though regression trees lack the global linearity assumption. We also show the practical use of this approach in detecting outliers in an ecological dataset collected in the Shenandoah Valley.


Download Citation

Nicholas Granered. Samantha C. Bates Prins. "Identifying Outlying Observations in Regression Trees." Missouri J. Math. Sci. 28 (1) 76 - 87, May 2016.


Published: May 2016
First available in Project Euclid: 19 September 2016

zbMATH: 1348.62134
MathSciNet: MR3549809
Digital Object Identifier: 10.35834/mjms/1474295357

Primary: 62G08

Keywords: backward-stepping , CART , influential observations , outlier , outlier detection , robust models

Rights: Copyright © 2016 Central Missouri State University, Department of Mathematics and Computer Science


Vol.28 • No. 1 • May 2016
Back to Top