Premium
Flexible and Robust Implementations of Multivariate Adaptive Regression Splines Within a Wastewater Treatment Stochastic Dynamic Program
Author(s) -
Tsai Julia C. C.,
Chen Victoria C. P.
Publication year - 2005
Publication title -
quality and reliability engineering international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.913
H-Index - 62
eISSN - 1099-1638
pISSN - 0748-8017
DOI - 10.1002/qre.708
Subject(s) - multivariate adaptive regression splines , mars exploration program , multivariate statistics , computer science , spline (mechanical) , mathematical optimization , regression , regression analysis , mathematics , machine learning , nonparametric regression , engineering , statistics , physics , structural engineering , astronomy
Abstract This paper presents an automatic and more robust implementation of multivariate adaptive regression splines (MARS) within the orthogonal array (OA)/MARS continuous‐state stochastic dynamic programming (SDP) method. MARS is used to estimate the future value functions in each SDP level. The default stopping rule of MARS employs the maximum number of basis functions M max , specified by the user. To reduce the computational effort and improve the MARS fit for the wastewater treatment SDP model, two automatic stopping rules, which automatically determine an appropriate value for M max , and a robust version of MARS that prefers lower‐order terms over higher‐order terms are developed. Computational results demonstrate the success of these approaches. Copyright © 2005 John Wiley & Sons, Ltd.