Testing relevant hypotheses in functional time series via self‐normalization

We develop methodology for testing relevant hypotheses about functional time series in a tuning‐free way. Instead of testing for exact equality, e.g. for the equality of two mean functions from two independent time series, we propose to test the null hypothesis of no relevant deviation. In the two‐sample problem this means that an L2 ‐distance between the two mean functions is smaller than a prespecified threshold. For such hypotheses self‐normalization, which was introduced in 2010 by Shao, and Shao and Zhang and is commonly used to avoid the estimation of nuisance parameters, is not directly applicable. We develop new self‐normalized procedures for testing relevant hypotheses in the one‐sample, two‐sample and change point problem and investigate their asymptotic properties. Finite sample properties of the tests proposed are illustrated by means of a simulation study and data examples. Our main focus is on functional time series, but extensions to other settings are also briefly discussed.

[1]  Joseph Berkson,et al.  Some Difficulties of Interpretation Encountered in the Application of the Chi-Square Test , 1938 .

[2]  D. Pollard.  Convergence of stochastic processes , 1984 .

[3]  J. Berger,et al.  Testing Precise Hypotheses , 1987 .

[4]  E. Carlstein.  Nonparametric Change-Point Estimation , 1988 .

[5]  L. Dümbgen.  The Asymptotic Behavior of Some Nonparametric Change-Point Estimators , 1991 .

[6]  Shein-Chung Chow,et al.  Design and Analysis of Bioavailability and Bioequivalence Studies , 1994 .

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

[8]  A. Munk,et al.  1 — α Equivariant Confidence Rules for Convex Alternatives are α/2–Level Tests—With Applications to the Multivariate Assessment of Bioequivalence , 1999 .

[9]  Shein-Chung Chow,et al.  Design and Analysis of Bioavailability and Bioequivalence Studies , 1994 .

[10]  Anirban DasGupta,et al.  Statistical tests for multivariate bioequivalence , 1999 .

[11]  Ricardo Fraiman,et al.  On the use of the bootstrap for estimating functions with functional data , 2006, Comput. Stat. Data Anal..

[12]  James O. Ramsay,et al.  Functional Data Analysis , 2005 .

[13]  Ingrid Van Keilegom,et al.  Two-sample tests in functional data analysis starting from discrete data , 2007 .

[14]  Qiang Zhang,et al.  Optimal rate of convergence for nonparametric change-point estimators for nonstationary sequences , 2007, 0710.4217.

[15]  A. Dasgupta.  Asymptotic Theory of Statistics and Probability , 2008 .

[16]  Alois Kneip,et al.  Common Functional Principal Components , 2006, 0901.4252.

[17]  Matthew Reimherr,et al.  Two sample inference in functional linear models , 2009 .

[18]  Piotr Kokoszka,et al.  Detecting changes in the mean of functional observations , 2009 .

[19]  S. Wellek.  Testing Statistical Hypotheses of Equivalence and Noninferiority , 2010 .

[20]  P. Kokoszka,et al.  Weakly dependent functional data , 2010, 1010.0792.

[21]  X. Shao,et al.  A self‐normalized approach to confidence interval construction in time series , 2010, 1005.2137.

[22]  X. Shao,et al.  Testing for Change Points in Time Series , 2010 .

[23]  Z. Harchaoui,et al.  Multiple Change-Point Estimation With a Total Variation Penalty , 2010 .

[24]  John H. Maddocks,et al.  Second-Order Comparison of Gaussian Random Functions and the Geometry of DNA Minicircles , 2010 .

[25]  Heng Peng,et al.  Two Samples Tests for Functional Data , 2010 .

[26]  Ron Reeder,et al.  Estimation of the mean of functional time series and a two‐sample problem , 2011, 1105.0019.

[27]  Katharine Hayhoe,et al.  Testing the structural stability of temporally dependent functional observations and application to climate projections , 2011 .

[28]  Mariela Sued,et al.  Testing the Equality of Covariance Operators , 2011 .

[29]  Piotr Kokoszka,et al.  Testing the Equality of Covariance Operators in Functional Samples , 2011, 1104.4049.

[30]  Victor M. Panaretos,et al.  Dispersion operators and resistant second-order functional data analysis , 2012 .

[31]  Piotr Kokoszka,et al.  Dependent Functional Data , 2012 .

[32]  Claudia Kirch,et al.  Detecting and estimating changes in dependent functional data , 2012, J. Multivar. Anal..

[33]  Siegfried Hörmann,et al.  On the Prediction of Stationary Functional Time Series , 2012, 1208.2892.

[34]  Piotr Kokoszka,et al.  Inference for Functional Data with Applications , 2012 .

[35]  Lajos Horváth,et al.  Weak invariance principles for sums of dependent random functions , 2013 .

[36]  X. Shao,et al.  A general approach to the joint asymptotic analysis of statistics from sub-samples , 2013, 1305.5618.

[37]  Piotr Kokoszka,et al.  Functional data analysis with increasing number of projections , 2013, J. Multivar. Anal..

[38]  M. Wendler,et al.  Sequential block bootstrap in a Hilbert space with application to change point analysis , 2014, 1412.0446.

[39]  Piotr Kokoszka,et al.  Testing stationarity of functional time series , 2014 .

[40]  Piotr Fryzlewicz,et al.  Wild binary segmentation for multiple change-point detection , 2014, 1411.0858.

[41]  Hsing,et al.  Functional Data Analysis , 2015 .

[42]  Xiaofeng Shao,et al.  Two sample inference for the second-order property of temporally dependent functional data , 2015, 1506.00847.

[43]  X. Shao,et al.  Self-Normalization for Time Series: A Review of Recent Developments , 2015 .

[44]  Theofanis Sapatinas,et al.  Bootstrap-based testing of equality of mean functions or equality of covariance operators for functional data , 2016 .

[45]  Ana-Maria Staicu,et al.  A two‐sample distribution‐free test for functional data with application to a diffusion tensor imaging study of multiple sclerosis , 2016, Journal of the Royal Statistical Society. Series C, Applied statistics.

[46]  Martin Wendler,et al.  Change-point detection and bootstrap for Hilbert space valued random fields , 2015, J. Multivar. Anal..

[47]  Jia Guo,et al.  Testing the equality of several covariance functions for functional data: A supremum-norm based test , 2018, Comput. Stat. Data Anal..

[48]  Ting Zhang,et al.  Unsupervised Self-Normalized Change-Point Testing for Time Series , 2018 .

[49]  H. Dette,et al.  Detecting deviations from second-order stationarity in locally stationary functional time series , 2018, Annals of the Institute of Statistical Mathematics.

[50]  A. Aue,et al.  Structural break analysis for spectrum and trace of covariance operators , 2018, Environmetrics.

[51]  Claudia Kirch,et al.  Detecting changes in the covariance structure of functional time series with application to fMRI data , 2019, Econometrics and Statistics.

[53]  Alexander Aue,et al.  Testing for stationarity of functional time series in the frequency domain , 2017, The Annals of Statistics.

[54]  Testing equality of autocovariance operators for functional time series , 2019, Journal of Time Series Analysis.