Estimating regression models with unknown break‐points

This paper deals with fitting piecewise terms in regression models where one or more break‐points are true parameters of the model. For estimation, a simple linearization technique is called for, taking advantage of the linear formulation of the problem. As a result, the method is suitable for any regression model with linear predictor and so current software can be used; threshold modelling as function of explanatory variables is also allowed. Differences between the other procedures available are shown and relative merits discussed. Simulations and two examples are presented to illustrate the method. Copyright © 2003 John Wiley & Sons, Ltd.

[1]  G. Box,et al.  Transformation of the Independent Variables , 1962 .

[2]  David W. Bacon,et al.  Estimating the transition between two intersecting straight lines , 1971 .

[3]  D. Griffiths,et al.  Hyperbolic regression - a model based on two-phase piecewise linear regression with a smooth transition between regimes , 1973 .

[4]  P. Feder.  The Log Likelihood Ratio in Segmented Regression , 1975 .

[5]  D. Hawkins.  POINT ESTIMATION OF THE PARAMETERS OF PIECEWISE REGRESSION MODELS. , 1976 .

[6]  E. Fowlkes,et al.  Some Algorithms for Linear Spline and Piecewise Multiple Linear Regression , 1976 .

[7]  R. Cook,et al.  Testing for Two-Phase Regressions , 1979 .

[8]  Asher Tishler,et al.  A Maximum Likelihood Method for Piecewise Regression Models with a Continuous Dependent Variable , 1981 .

[9]  R. Tibshirani,et al.  Generalized additive models for medical research , 1986, Statistical methods in medical research.

[10]  C. Cox,et al.  Threshold dose-response models in toxicology. , 1987, Biometrics.

[11]  K Ulm,et al.  A statistical method for assessing a threshold in epidemiological studies. , 1991, Statistics in medicine.

[12]  J L Bosson,et al.  Strategies for graphical threshold determination. , 1991, Computer methods and programs in biomedicine.

[13]  Detecting break points in generalised linear models , 1992 .

[14]  J. Mackenbach,et al.  Outdoor air temperature and mortality in The Netherlands: a time-series analysis. , 1993, American journal of epidemiology.

[15]  Chris Gennings,et al.  Threshold Models for Combination Data from Reproductive and Developmental Experiments , 1995 .

[16]  R. Carroll,et al.  Segmented regression with errors in predictors: semi-parametric and parametric methods. , 1997, Statistics in medicine.

[17]  E. Guallar,et al.  Use of two-segmented logistic regression to estimate change-points in epidemiologic studies. , 1998, American journal of epidemiology.

[18]  Christoff Gössl,et al.  Bayesian analysis of logistic regression with an unknown change point and covariate measurement error , 2001 .

[19]  S. Julious.  Inference and estimation in a changepoint regression problem , 2001 .

[20]  J. Daurès,et al.  Regression splines for threshold selection in survival data analysis. , 2001, Statistics in Medicine.

[21]  J. A. Branco,et al.  Models for the estimation of a ‘no effect concentration’ , 2002 .