Undocumented Changepoint Detection by Nonparametric Procedure in a Two-Phase Linear Regression Model

• Activity Number: 405 - Nonparametric Testing in Complex Data Settings
• Type: Contributed
• Date/Time: Tuesday, August 1, 2017 : 2:00 PM to 3:50 PM
• Sponsor: Section on Nonparametric Statistics
• Author(s): Jing Sun* and Sunil Mathur and Deepak Sakate
• Companies: Augusta University and Augusta University and Shivaji University
• Keywords: least squares estimator ; F test ; rank regression ; two phase linear regression ; non-normal error

Abstract

Changepoint detection in linear regression has many applications in climatology, bioinformatics, finance, oceanography and medical imaging. In this article, we propose a procedure to detect changepoint in linear regression based on a nonparametric method. The proposed procedure performs well for non-normal error distribution and does not require the assumption of normal distribution. A simulation study is conducted to compare the performance of the proposed procedure with the existing procedure, considering the error distribution as Laplace, Student's t, and mixture of normal distributions. The simulation study indicates that the proposed procedure outperforms its competitor. A real-life example is used to illustrate the working procedure.