Work

A New Two-stage Method for Nonparametric Regression With Jump Points

Year: 2008

Type: book-chapter

Abstract: In this chapter, a two-staged method is presented for nonparametric regression with jump points. After the rough location of all the possible jump points are identified using the existing efficient kernel method, a smoothing spline function is used to approximate each segment of the regression function. A time scaling transformation is derived so as to map the undecided jump points into fixed points. This approximation problem is formulated as an optimization problem which can be solved by many existing techniques. The method is applied to several examples. The results obtained show that the method is highly efficient

Source: World scientific series on nonlinear science, series A

Parent work: Control of Chaos in Nonlinear Circuits and Systems

DOI: 10.1142/9789812790576_0004

Authors: C. Z. Wu, C. M. Liu, K. L. Teo, Q. X. Shao

Institutions: Chongqing Normal University, Curtin University, Commonwealth Scientific and Industrial Research Organisation

Language: English

Topic: Statistical Methods and Inference

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W1509442461