Journal of applied mathematics & informatics

The Korean Society for Computational and Applied Mathematics (한국전산응용수학회)
권호 표지

CHANGE-POINT DETECTION WITH SPLIT LINEAR FITS

  • Kim, Jae-Hee (Department of Statistics, Duksung Women's University)
  • Published : 2001.05.01

⟨ Previous Next ⟩

Abstract

A procedure of detecting change-points is considered with split linear fitting idea from Hall and Titterington(1992). At each given point, left, central and right linear fits are compared to detect the discontinuities or change-points. A simulation study is done with various types of change models and shows that the suggested technique can be a flexible data-analytic tool.

Keywords

References

  1. The Annals of Statistics v.16 Nonparametric change-point estimation E.Carlstein
  2. Technometrics v.34 Edge-preserving and Peak-preserving smoothing P.Hall;M.Titterington
  3. Communications in Statistics, B v.15 A Simple Least Squares Method for Estimating a Change in Mean D.L.Hawkins
  4. Biometrika v.57 Inference about the change-point in a sequence of random variables D.V.Hinkley
  5. Korean Journal of Comutational and Applied Mathematics v.7 no.2 A nonparametric change-point estimator using window in mean change model Jaehee Kim;Heeyoun Jang
  6. Technometrics v.28 Smoothing with split linear fits J.A.McDonald;A.B.Owen
  7. Applied Statistics v.28 A nonparametric approach to the changepoint problem A.N.Pettitt
  8. Communications in Statistics - Simulation and Computation, B v.19 Comparisons of changepoint estimators S.M.Scariano;T.A.Watkins
  9. Communication in Statistics - Simulation and Computation, B v.17 A nonparametric test for detecting changes in location E.Schechtman
  10. Technometrics v.40 no.2 A local polynomial jump-detection algorithm in nonparametric regression P.Qui;B.Yandell