Abstract
It may happen that the behavior of a multivariate time series is such that the underlying joint distribution is gradually moving from one distribution to another between unknown times of change. Under this context of a possible gradual-change, tests of change-point detection in the dependence structure of multivariate series are developed around the associated sequence of Spearman matrices. It is formally established that the proposed test statistics for that purpose are asymptotically marginal-free under a general strong-mixing assumption, and written as functions of integrated Brownian bridges. Consistent estimators of the pair of times of change, as well as of the before-the-change and after-the-change Spearman matrices, are also proposed. A simulation study examines the sampling properties of the introduced tools, and the methodologies are illustrated on a synthetic dataset.
Similar content being viewed by others
References
Andrews, D. W. K. (1991). Heteroskedasticity and autocorrelation consistent covariance matrix estimation. Econometrica, 59(3), 817–858.
Aue, A., Steinebach, J. (2002). A note on estimating the change-point of a gradually changing stochastic process. Statistics & Probability Letters, 56(2), 177–191.
Bissell, A. F. (1984). The performance of control charts and cusums under linear trend. Journal of the Royal Statistical Society: Series C (Applied Statistics), 33(2), 145–151.
Brodsky, B. E., Darkhovsky, B. S. (1993). Nonparametric methods in change-point problems. Mathematics and its Applications, Vol. 243. Kluwer Academic Publishers Group, Dordrecht.
Bücher, A., Kojadinovic, I., Rohmer, T., Segers, J. (2014). Detecting changes in cross-sectional dependence in multivariate time series. Journal of Multivariate Analysis, 132, 111–128.
Bücher, A., Ruppert, M. (2013). Consistent testing for a constant copula under strong mixing based on the tapered block multiplier technique. Journal of Multivariate Analysis, 116, 208–229.
Carlstein, E. (1988). Nonparametric change-point estimation. The Annals of Statistics, 16(1), 188–197.
Dehling, H., Vogel, D., Wendler, M., Wied, D. (2017). Testing for changes in Kendall’s tau. Econometric Theory, 33(6), 1352–1386.
Dehling, H., Vuk, K., Wendler, M. (2022). Change-point detection based on weighted two-sample U-statistics. Electronic Journal of Statistics, 16(1), 862–891.
Fermanian, J. -D., Radulović, D., Wegkamp, M. H. (2004). Weak convergence of empirical copula processes. Bernoulli, 10, 847–860.
Gan, F. (1992). Cusum control charts under linear drift. Journal of the Royal Statistical Society: Series D (The Statistician), 41(1), 71–84.
Gombay, E., Horváth, L. (1995). An application of \(U\)-statistics to change-point analysis. Acta Universitatis Szegediensis. Acta Scientiarum Mathematicarum, 60(1–2), 345–357.
Gombay, E., Horváth, L. (1999). Change-points and bootstrap. Environmetrics, 10(6), 725–736.
Hušková, M. (1999). Gradual changes versus abrupt changes. Journal of Statistical Planning and Inference, 76(1–2), 109–125.
Hušková, M, Meintanis, S. G. (2006a). Change point analysis based on empirical characteristic functions. Metrika, 63(2), 145–168.
Hušková, M., Meintanis, S. G. (2006b). Change-point analysis based on empirical characteristic functions of ranks. Sequential Analysis. Design Methods & Applications, 25(4), 421–436.
Inoue, A. (2001). Testing for distributional change in time series. Econometric Theory, 17(1), 156–187.
Kander, Z., Zacks, S. (1966). Test procedures for possible changes in parameters of statistical distributions occurring at unknown time points. Annals of Mathematical Statistics, 37, 1196–1210.
Kojadinovic, I., Quessy, J. -F., Rohmer, T. (2016). Testing the constancy of Spearman’s rho in multivariate time series. Annals of the Institute of Statistical Mathematics, 68(5), 929–954.
Lombard, F. (1987). Rank tests for changepoint problems. Biometrika, 74(3), 615–624.
Nasri, B. R., Rémillard, B. N., Bahraoui, T. (2022). Change-point problems for multivariate time series using pseudo-observations. Journal of Multivariate Analysis, 187, 104857.
Nelsen, R. B. (2006). An introduction to copulas. Springer Series in Statistics, second edition, Springer, New York.
Page, E. S. (1955). A test for a change in a parameter occurring at an unknown point. Biometrika, 42, 523–527.
Parzen, E. (1962). On estimation of a probability density function and mode. Annals of Mathematical Statistics, 33, 1065–1076.
Pettitt, A. (1979). A non-parametric approach to the change point problem. Applied Statistics, 28(2), 126–135.
Quessy, J. -F. (2019). Consistent nonparametric tests for detecting gradual changes in the marginals and the copula of multivariate time series. Statistical Papers, 60(3), 367–396.
Quessy, J. -F, Saïd, M., Favre, A. -C. (2013). Multivariate Kendall’s tau for change-point detection in copulas. Canadian Journal of Statistics, 41(1), 65–82.
Rio, E. (2000). Théorie asymptotique des processus aléatoires faiblement dépendants. Mathématiques et Applications. Berlin: Springer-Verlag.
Sklar, A. (1959). Fonctions de répartition à \(n\) dimensions et leurs marges. Publications de l’Institut de statistique de l’Université de Paris, 8, 229–231.
van der Vaart, A. W., Wellner, J. A. (1996). Weak convergence and empirical processes: With applications to statistics. Springer Series in Statistics. New York: Springer-Verlag.
Vogt, M., Dette, H. (2015). Detecting gradual changes in locally stationary processes. The Annals of Statistics, 43(2), 713–740.
Wied, D., Dehling, H., van Kampen, M., Vogel, D. (2014). A fluctuation test for constant Spearman’s rho with nuisance-free limit distribution. Computational Statistics & Data Analysis, 76, 723–736.
Acknowledgements
The author acknowledges financial support by individual grants from the Natural Sciences and Engineering Research Council of Canada (NSERC).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
A Proofs of the main results
A Proofs of the main results
1.1 A.1: Proof of Proposition 1
From the definition of \({\mathscr {S}}_{\ell \ell '}^\textrm{Sp} = (\rho ^\textrm{Sp}_{\ell \ell ',1}, \ldots , \rho ^\textrm{Sp}_{\ell \ell ',T})\) and in view of (4), a direct computation yields
It readily follows that \(\varUpsilon ^\textbf{k}= (\varSigma _G^\textrm{Sp} - \varSigma _F^\textrm{Sp}) \, \langle \varvec{\textbf{w}}^\textbf{k}, \varvec{\textbf{w}}^{\textbf{k}_0} \rangle \). \(\square \)
1.2 A.2: Proof of Proposition 2
First recall that for any \(\ell <\ell ' \in \{1,\ldots ,d\}\), one can associate \(j \in \{ 1, \ldots , L \}\) via the rule \(j = (\ell -1) d + \ell ' - {\ell +1 \atopwithdelims ()2}\). Letting \({{\widetilde{\textbf{u}}}}_j = (\textbf{1}_{\ell -1},u_\ell ,\textbf{1}_{\ell '-\ell -1},u_{\ell '},\textbf{1}_{d-\ell '})\), one can write
where \({\widehat{\mathbb {L}}}^\textbf{k}\) is the empirical process defined for \(\textbf{u}\in [0,1]^d\) by
It will now be shown that \({\widehat{\mathbb {L}}}^\textbf{k}\) is asymptotically equivalent to
Letting \(\widehat{\textbf{F}}^{-1}(\textbf{u}) = ({\widehat{F}}_1^{-1}(u_1), \ldots , {\widehat{F}}_d^{-1}(u_d))\), one can write
Under the assumption that the \(\alpha \)-mixing coefficients of \((\textbf{U}_t)_{t\in \mathbb {Z}}\) are such that \(\alpha (r) = O(r^{-4-d(1+\epsilon )})\) for some \(\epsilon \in (0,1/4]\), one can invoke Proposition 1 of Quessy (2019) and conclude that \({{\widetilde{\mathbb {L}}}}^\textbf{k}\) converges weakly in the space \(\varDelta \times \ell ^\infty ([0,1]^d)\) to a centered Gaussian process \(\mathbb {L}^\textbf{k}\) such that for \((\textbf{k},\textbf{u}),(\textbf{k}',\textbf{u}') \in \varDelta \times [0,1]^d\),
where for \(\textbf{k}= (k_1,k_2)\) and \(\textbf{k}' = (k_1',k_2')\),
Since \(\sqrt{T}(\widehat{\textbf{F}}^{-1}(\textbf{u})-\textbf{u})\) converges weakly and \({{\widetilde{\mathbb {L}}}}^\textbf{k}\) is asymptotically continuous, the second expression on the right of inequality (14) converges in probability to zero. To deal with the first expression on the right of inequality (14), note that
Invoking Lemma 1 in Quessy (2019) that establishes that
where \(K_1 = \lfloor T k_1 \rfloor \) and \(K_2 = \lfloor T k_2 \rfloor \), one has
Now proceeding as in Fermanian et al. (2004), define the grid \(G_T = \{(i_1,...,i_d)/T: i_1, \ldots , i_d \in \{1,\ldots ,T\} \}\) and observe that \(\mathbb {I}(\widehat{\textbf{F}}(\textbf{U}_t) \le \textbf{u}) = \mathbb {I}(\textbf{U}_t \le \widehat{\textbf{F}}^{-1}(\textbf{u}))\) when \(\textbf{u}\in G_T\). From the fact that
one can write
It follows that
This shows that as \(T\rightarrow \infty \)
As a consequence, referring back to (13),
One can then write
An application of the Continuous mapping Theorem then ensures that \(\sqrt{T} \, \mathscr {V}({\widehat{\varUpsilon }}^\textbf{k}) / 12\) converges weakly to a vector of processes of the form \(\mathbb {V}(\textbf{k}) = \left( \mathbb {V}_1(\textbf{k}), \ldots , \mathbb {V}_L(\textbf{k}) \right) \), where
Therefore, \(\mathbb {V}\) is a vector of centered Gaussian processes such that for \(j' = (m-1) d + m' - {m+1 \atopwithdelims ()2}\) associated to \(m<m' \in \{1,\ldots ,d\}\), its covariance structure is managed for \(\textbf{k}, \textbf{k}' \in \varDelta \) by
Hence, \(\textrm{E}\{ \mathbb {V}(\textbf{k})^\top \mathbb {V}(\textbf{k}') \} = \varLambda (\textbf{k},\textbf{k}') \, \varOmega \) and
Since the covariance function of the integrated Brownian bridge is \(\textrm{E}\{ {{\widetilde{\mathbb {B}}}}(\textbf{k}) \, {{\widetilde{\mathbb {B}}}}(\textbf{k}') \} = \varLambda (\textbf{k},\textbf{k}')\), the covariance structure \(\varLambda (\textbf{k},\textbf{k}') \, I_L\) is the same as that of a vector \(({{\widetilde{\mathbb {B}}}}_1(\textbf{k}), \ldots , {{\widetilde{\mathbb {B}}}}_L(\textbf{k}))\) of independent integrated Brownian bridges. It follows that \(\sqrt{T} \, \mathscr {V}({\widehat{\varUpsilon }}^\textbf{k}) \, \varOmega ^{-1/2} / 12\) converges weakly to \(({{\widetilde{\mathbb {B}}}}_1(\textbf{k}), \ldots , {{\widetilde{\mathbb {B}}}}_L(\textbf{k}))\). \(\square \)
1.3 A.3: Proof of Proposition 3
From the conclusion of Proposition 2 and the Continuous mapping Theorem,
which completes the proof. \(\square \)
1.4 A.4: Proof of Proposition 4
The first step of the proof consists to write
where \({\widehat{\mathbb {L}}}^\textbf{k}\) is the empirical process defined for \(\textbf{u}\in [0,1]^d\) by
By arguments similar as those in the proof of Proposition 2, \({\widehat{\mathbb {L}}}^\textbf{k}\) is asymptotically equivalent to
It is easy to see that \({{\widetilde{\mathbb {L}}}}^\textbf{k}\) converges weakly to a non-degenerate centered Gaussian process whose covariance structure is characterized by the finite-dimensional structure of \({{\widetilde{\mathbb {L}}}}^\textbf{k}\). As a consequence,
Since \(\varSigma _F^\textrm{Sp} \ne \varSigma _G^\textrm{Sp}\), one has in probability that
where \(\varLambda (\textbf{k},\textbf{k}_0) = \lim _{T\rightarrow \infty } \langle \textbf{w}^\textbf{k}, \textbf{w}^{\textbf{k}_0} \rangle \). Invoking the argmax continuous mapping Theorem (see Theorem 3.2.2 of van der Vaart and Wellner 1996), one can conclude that in probability,
\(\square \)
About this article
Cite this article
Quessy, JF. Gradual change-point analysis based on Spearman matrices for multivariate time series. Ann Inst Stat Math 76, 423–446 (2024). https://doi.org/10.1007/s10463-023-00891-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10463-023-00891-5