Abstract
This paper studies the change-point problem for a general parametric, univariate or multivariate family of distributions. An information theoretic procedure is developed which is based on general divergence measures for testing the hypothesis of the existence of a change. For comparing the exact sizes of the new test-statistic using the criterion proposed in Dale (J R Stat Soc B 48–59, 1986), a simulation study is performed for the special case of exponentially distributed random variables. A complete study of powers of the test-statistics and their corresponding relative local efficiencies, is also considered.
Similar content being viewed by others
References
Chen J, Gupta AK (2000) Parametric statistical change point analysis. Birkhauser Boston Inc., Boston
Chen J, Gupta AK (2001) On change point detection and estimation. Commun Stat Simul Comput 30:665–697
Chen J, Gupta AK (2004) Statistical inference on covariance change points in Gaussian model. Statistics 38:17–28
Chen J, Gupta AK, Pan J (2006) Information criterion and change point problem for regular models. Sankhyā: Indian J Stat Ser A 68:252–282
Cressie N, Pardo L, Pardo MC (2003) Size and power considerations for testing loglinear models using ϕ-divergence test statistics. Stat Sin 13:550–570
Csörgö M, Horváth L (1998) Limit theorems in change-point analysis. Wiley, New York
Dale JR (1986) Asymptotic normality of goodness-of-fit statistics for sparse product multinomials. J R Stat Soc B 48:48–59
De Long DM (1981) Crossing probabilities for a square root boundary by a Bessel process. Commun Stat–Theory Methods 10:2197–2213
Estrella A (2003) Critical values and p values of bessel process distributions: computation and application to structural break tests. Econ Theory 19:1128–1143
Gombay E, Horváth L (1996) On the rate of approximations for maximum likelihood tests in change-point models. J Multivar Anal 56:120–152
Haccou P, Meelis E, Van der Geer S (1985) On the likelihood ratio test for a change point in a sequence of independent exponentially distributed random variables. Report MS-R8507, Centre for Mathematics and Computer Science, Amsterdam
Haccou P, Meelis E, Van der Geer S (1988) The likelihood ratio test for the change point problem for exponentially distributed random variables. Stoch Process Appl 27:121–139
Hawkins DL (1987) A test for a change point in a parametric model based on a maximal wald-type statistic. Sankhyā: Indian J Stat Ser A 49:368–376
Horváth L, Serbinowska M (1995) Testing for changes in multinomial observations: the lindisfarne scribes problem. Scand J Stat 22:371–384
Martin N, Pardo L (2012) Poisson-loglinear modeling with linear constraints on the expected cell frequencies. Sankhya B: Indian J Stat 74:238–267
Morales D, Pardo L, Pardo MC, Vajda I (2004) Rénryi statistics for testing composite Hypothesis for in general exponential models. Statistic 38(2):133–147
Pardo L (2006) Statistical inference based on divergence measures. Chapman & Hall/CRC, Boca Raton
Pettitt AN (1980) A simple cumulative sum type statistic for the change-point problem with zero-one observations. Biometrika 67(1):79–84
Read TRC, Cressie NAC (1988) Goodness of fit statistics for discrete multivariate data. Springer, New York
Sen PK (1981) Sequential nonparametrics: invariance principles and statistical inference. Wiley, New York
Sen PK, Srivastava MS (1980) On tests for detecting change in the multivariate mean. Tech. Report No. 3, University of Toronto
Sen PK, Singer JM (1993) Large sample methods in statistics: an introduction with applications. Chapman & Hall, New York
Siegmund D, Venkatraman ES (1995) Using the generalized likelihood ratio statistic for sequential detection of a change-point. Ann Stat 23:255–271
Srivastava MS, Worsley KJ (1986) Likelihood ratio tests for a change in the multivariate normal mean. J Am Stat Assoc 81:199–204
Vostrikova LJ (1981) Detecting disorder in multidimensional random processes. Sov Math Dokl 24:55–59
Worsley KJ (1986) Confidence regions and test for a change-point in a sequence of exponential family random variables. Biometrika 73:91–104
Yang TY, Kuo L (2001) Bayesian binary segmentation procedure for a Poisson process with multiple changepoints. J Comput Graph Stat 10:772–785
Author information
Authors and Affiliations
Corresponding author
Additional information
N. Martín, L. Pardo and K. Zografos were partially supported by grant MTM 2012-33740
Rights and permissions
About this article
Cite this article
Batsidis, A., Martín, N., Pardo, L. et al. ϕ-Divergence Based Procedure for Parametric Change-Point Problems. Methodol Comput Appl Probab 18, 21–35 (2016). https://doi.org/10.1007/s11009-014-9398-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11009-014-9398-3