Robust bent line regression
From MaRDI portal
Publication:514183
DOI10.1016/J.JSPI.2017.01.001zbMATH Open1360.62390arXiv1606.02234OpenAlexW2964246378WikidataQ47930727 ScholiaQ47930727MaRDI QIDQ514183FDOQ514183
Authors: Qunhua Li, Feipeng Zhang 
Publication date: 28 February 2017
Published in: Journal of Statistical Planning and Inference (Search for Journal in Brave)
Abstract: We introduce a rank-based bent linear regression with an unknown change point. Using a linear reparameterization technique, we propose a rank-based estimate that can make simultaneous inference on all model parameters, including the location of the change point, in a computationally efficient manner. We also develop a score-like test for the existence of a change point, based on a weighted CUSUM process. This test only requires fitting the model under the null hypothesis in absence of a change point, thus it is computationally more efficient than likelihood-ratio type tests. The asymptotic properties of the test are derived under both the null and the local alternative models. Simulation studies and two real data examples show that the proposed methods are robust against outliers and heavy-tailed errors in both parameter estimation and hypothesis testing.
Full work available at URL: https://arxiv.org/abs/1606.02234
Recommendations
Nonparametric estimation (62G05) Nonparametric hypothesis testing (62G10) Linear regression; mixed models (62J05) Applications of statistics to economics (62P20) Asymptotic properties of parametric tests (62F05) Sequential statistical analysis (62L10)
Cites Work
- Wild binary segmentation for multiple change-point detection
- Title not available (Why is that?)
- Testing for Regime Switching
- The Estimation of the Parameters of a Linear Regression System Obeying Two Separate Regimes
- Using penalized contrasts for the change-point problem
- Nonparametric model checks for regression
- Tests for Parameter Instability and Structural Change With Unknown Change Point
- Inference When a Nuisance Parameter Is Not Identified Under the Null Hypothesis
- Convergence of stochastic processes
- The Cusum Test with Ols Residuals
- Testing for Threshold Effects in Regression Models
- Nonparametric Estimate of Regression Coefficients
- Consistency and limiting distribution of the least squares estimator of a threshold autoregressive model
- On asymptotic distribution theory in segmented regression problems - identified case
- Tests of the Hypothesis that a Linear Regression System Obeys Two Separate Regimes
- Fitting Segmented Polynomial Regression Models Whose Join Points have to be Estimated
- Estimating Regression Coefficients by Minimizing the Dispersion of the Residuals
- Testing for Parameter Constancy in Linear Regressions: An Empirical Distribution Function Approach
- Sample Criteria for Testing Outlying Observations
- Model selection by LASSO methods in a change-point model
- A Lack-of-Fit Test for Quantile Regression
- Inference under right censoring for transformation models with a change-point based on a covariate threshold
- Testing for structural change in regression quantiles
- Bent line quantile regression with application to an allometric study of land mammals' speed and mass
- Segmented model selection in quantile regression using the minimum description length principle
- Robust nonparametric statistical methods
- Testing for change points due to a covariate threshold in quantile regression
- Some Hypotheses Concerning Two Phase Regression Lines
- Selecting the number of change-points in segmented line regression
- Inference about the intersection in two-phase regression
Cited In (10)
- Robust algorithms for multiphase regression models
- Robust change point estimation in two-phase linear regression models: an application to metabolic pathway data
- A continuous threshold expectile model
- Generalized linear-quadratic model with a change point due to a covariate threshold
- Composite change point estimation for bent line quantile regression
- A bent line Tobit regression model with application to household financial assets
- Segmented Correspondence Curve Regression for Quantifying Covariate Effects on the Reproducibility of High-Throughput Experiments
- Real-time detection of a change-point in a linear expectile model
- Bent line quantile regression with application to an allometric study of land mammals' speed and mass
- Estimation and inference for multikink expectile regression with longitudinal data
Uses Software
This page was built for publication: Robust bent line regression
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q514183)
