Regression trees with splitting based on changes of dependencies among covariates

Article type: Research Article

Authors: Boskabadi, Mostafa | Doostparast, Mahdi^*

Affiliations: Department of Statistics, Ferdowsi University of Mashhad, Khorasan Razavi, Iran

Correspondence: [*] Corresponding author: Mahdi Doostparast, Department of Statistics, Ferdowsi University of Mashhad, Khorasan Razavi, Iran. Tel./Fax: +98 51 38828605; E-mail: doustparast@um.ac.ir.

Abstract: Regression trees are powerful tools in data mining for analyzing data sets. Observations are usually divided into homogeneous groups, and then statistical models for responses are derived in the terminal nodes. This paper proposes a new approach for regression trees that considers the dependency structures among covariates for splitting the observations. The mathematical properties of the proposed method are discussed in detail. To assess the accuracy of the proposed model, various criteria are defined. The performance of the new approach is assessed by conducting a Monte-Carlo simulation study. Two real data sets on classification and regression problems are analyzed by using the obtained results.

Keywords: Regression tree, dependence, copula function, hypothesis testing

DOI: 10.3233/IDA-205140

Journal: Intelligent Data Analysis, vol. 25, no. 3, pp. 687-710, 2021