Nonparametric tests for change-point detection à la Gombay and Horváth

The nonparametric test for change-point detection proposed by Gombay and Horvath is revisited and extended in the broader setting of empirical process theory. The resulting testing procedure for potentially multivariate observations is based on a sequential generalization of the functional multiplier central limit theorem and on modifications of Gombay and Horvath's seminal approach that appears to improve the finite-sample behavior of the tests. A large number of candidate test statistics based on processes indexed by lower-left orthants and half-spaces are considered and their performance is studied through extensive Monte Carlo experiments involving univariate, bivariate and trivariate data sets. Finally, practical recommendations are provided and the tests are illustrated on trivariate hydrological data.

[1]  Lajos Horváth,et al.  Testing for changes using permutations of U-statistics , 2005 .

[2]  Fabrizio Durante,et al.  On the return period and design in a multivariate framework , 2011 .

[3]  Jon A. Wellner,et al.  Weak Convergence and Empirical Processes: With Applications to Statistics , 1996 .

[4]  L. Horváth,et al.  Invariance principles for changepoint problems , 1988 .

[5]  M. Kosorok Introduction to Empirical Processes and Semiparametric Inference , 2008 .

[6]  Jaromír Antoch,et al.  Permutation tests in change point analysis , 2001 .

[7]  Dietmar Ferger,et al.  On the power of nonparametric changepoint-tests , 1994 .

[8]  Edit Gombay,et al.  Change‐points and bootstrap , 1999 .

[9]  M. Sklar Fonctions de repartition a n dimensions et leurs marges , 1959 .

[10]  Lajos Horváth,et al.  Limit theorems for permutations of empirical processes with applications to change point analysis , 2007 .

[11]  Pál Révész Limit theorems in probability and statistics , 1984 .

[12]  Joseph P. Romano A Bootstrap Revival of Some Nonparametric Distance Tests , 1988 .

[13]  Richard M. Dudley,et al.  Invariance principles for sums of Banach space valued random elements and empirical processes , 1983 .

[14]  A. Inoue TESTING FOR DISTRIBUTIONAL CHANGE IN TIME SERIES , 2001, Econometric Theory.

[15]  B. Brodsky,et al.  Nonparametric Methods in Change Point Problems , 1993 .

[16]  Edit Gombay,et al.  Rates of convergence for U-statistic processes and their bootstrapped versions , 2002 .