Abstract
Likelihood ratio type test statistics are suggested for detecting changes in means of coordinates of observed random vectors. It is supposed that changes in different coordinates need not to occur at the same time. Under the assumption of no change, asymptotic distributions of the proposed test statistics are given by distributions of maxima of \(\chi ^2\) random fields. High-level exceedance probabilities of non-homogeneous \(\chi ^2\) fields may be applied to get approximate asymptotic critical values.
Similar content being viewed by others
References
Albin JMP (1990) On extremal theory for stationary processes. Ann Probab 18:92–128
Andrews DWK (1993) Tests for parameter instability and structural change with unknown change point. Econometrica 61:821–856
Antoch J, Jarušková D (2013) Testing for multiple change points. Comput Stat 28:2161–2183
Camuffo D, Jones P (eds) (2002) Improved understanding of past climatic variability from early daily European instrumental sources. Clim Change 53:1–3
Chan HP, Lai TL (2006) Maxima of asymptotically Gaussian random fields and moderate deviation approximations to boundary crossing probabilities of sums of random variables with multidimensional indices. Ann Probab 34:80–121
Chen J, Gupta AK (2000) Parametrical change point analysis. Birkhaüser, New York
Csörgő M, Horváth L (1997) Limit theorems in change point analysis. Wiley, New York
Guédon Y (2013) Exploring the latent segmentation space for the assessment of multiple change-point models. Comput Stat 28:2641–2678
Hidalgo J, Seo MH (2013) Testing for structural stability in the whole sample. J Econ 175:84–93
Horváth L, Kokoszka P (1999) Testing for changes in multivariate dependent observations with an application to temperature changes. J Multivar Anal 68:96–119
Horváth L, Rice G (2014) Extensions of some classical methods in change point analysis. Test 23:219–255
Jandhyala VK, Fotopoulos SB, MacNeil I, Liu P (2013) Inference for single and multiple change-points in time series. J Time Ser Anal 34:423–446
Jarušková D (2010) Asymptotic behaviour of a test statistic for detection of change in mean of vectors. J Stat Plan Inference 140:616–625
Jarušková D, Piterbarg VI (2011) Log-likelihood ratio test for detecting transient change. Stat Probab Lett 81:552–559
Jarušková D (2011) Detection of transient change in mean—a linear behavior inside epidemic interval. Kybernetika 47:1–14
Kabluchko Z (2008) Extreme-value analysis of standardized Gaussian increaments. arXiv:0706.1849v3 [math.PR]
Killick R, Fearnhead P, Eckley IA (2012) Optimal detection of change-points with a linear computational cost. J Am Stat Assoc 107:1590–1598
Piterbarg VI (1996) Asymptotic methods in theory of Gaussian processes and fields. AMS, Providence
Reschenhofer E, Preinerstorfer D, Steinberger L (2013) Non-monotonic penalizing for the number of structural breaks. Comput Stat 28:2585–2598
Siegmund D (1986) Boundary crossing probabilities and statistical applications. Ann Stat 14:361–404
Tan Z, Hashorva E (2013) Exact asymptotics a limit theorems for supremum of stationary \(\chi \)-processes over a random interval. Stoch Process Appl 123:2983–2998
Zhang NR, Siegmund DO (2012) Model selection for high-dimensional multisequence change-point problems. Stat Sin 22:1507–1538
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by Grant GAČR 403-15-09663S.
Rights and permissions
About this article
Cite this article
Jarušková, D. Detecting non-simultaneous changes in means of vectors. TEST 24, 681–700 (2015). https://doi.org/10.1007/s11749-015-0429-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11749-015-0429-3
Keywords
- Non-simultaneous changes
- Multiple change point detection
- Log-likelihood ratio test statistics
- Asymptotic distribution
- Extremes of \(\chi ^2\) random fields