Bayesian like R- and M- estimators of change points

• Autorzy: Jaromír Antoch , Marie Husková
• Języki publikacji: EN

Abstrakty

EN

The purpose of this paper is to study Bayesian like R- and M-estimators of change point(s). These estimators have smaller variance than the related argmax type estimators. Confidence intervals for the change point based on the exchangeability arguments are constructed. Finally, theoretical results are illustrated on the real data set.

Słowa kluczowe

EN

estimators of change point; rank statistics; M- and R-estimators; fixed and local changes

Kategorie tematyczne

• 60F17: Functional limit theorems; invariance principles
• 62G20: Asymptotic properties
• 62E20: Asymptotic distribution theory

• Wydawca: Faculty of Mathematics, Computer Science and Econometrics, University of Zielona Góra
• Czasopismo: Discussiones Mathematicae Probability and Statistics
• Rocznik: 2000
• Tom: 20
• Numer: 1
• Strony: 115-134

Daty

wydano

2000

otrzymano

1999-02-20

Twórcy

autor

Jaromír Antoch

• Department of Statistics, Charles University, Sokolovská 83, CZ - 186 75 Praha 8 - Karlín, Czech Republic

autor

Marie Husková

• Department of Statistics, Charles University, Sokolovská 83, CZ - 186 75 Praha 8 - Karlín, Czech Republic

Bibliografia

• [1] J. Antoch and M. Husková, Estimators of changes, Nonparametrics, Asymptotics and Time Series, Ghosh S. ed., M. Dekker, (1998a), 533-578.
• [2] J. Antoch and M. Husková, Bayesian like estimators of changes, 1998b, J. Stat. Plan. Infer., submitted.
• [3] J. Antoch and J.Á. Vísek, Robust estimation in linear model and its computational aspects, Computational Aspects of Model Choice, Physica Verlag, Heidelberg, Antoch J. ed., (1992), 39-104.
• [4] G.W. Cobb, The problem of the Nile: Conditional solution to a change-point problem, Biometrika 65 (1978), 243-251.
• [5] M. Csörgo and L. Horváth, Limit Theorems in Change-Point Analysis, J. Wiley, New York 1997.
• [6] L. Dümbgen, The asymptotic behavior of some nonparametric change-point estimators, Ann. Statist. 19 (1991), 1471-1495.
• [7] E. Gombay and M. Husková, Rank based estimators of the change-point, J. Stat. Plan. Infer. 67 (1997), 137-154.
• [8] D. Hinkley and E. Schechtman, Conditional bootstrap methods in the mean-shift model, Biometrika 74 (1987), 85-93.
• [9] P. J. Huber, Robust Statitics, J. Wiley, New York 1981.
• [10] M. Husková, Limit theorems for rank statistics, Statist. and Probab. Letters 30 (1997a), 45-55.
• [11] M. Husková, Limit theorems for M-processes via rank statistics processes, Advances in Combinatorial Methods with Applications to Probability and Statistics, Balakrishnan N. ed., (1997b), 527-533.
• [12] M. Husková, Multivariate rank statistics processes and change-point analysis, Volume of Saleh, 1997c (to appear).
• [13] I. A. Ibragimov and R. Z. Has'minskii, Statistical Estimation. Asymptotic Theory, Springer Verlag, Heidelberg 1981.
• [14] Y. Ritov, Asymptotic efficient estimation of the change-point with unknown distribution, Ann. Statist. 18 (1990), 1829-1839.

Identyfikatory

DOI

10.7151/dmps.1007