On testing for independence between the innovations of several time series. (English. French summary) Zbl 1333.62208

Duchesne, Pierre; Ghoudi, Kilani; Rémillard, Bruno

Can. J. Stat. 40, No. 3, 447-479 (2012).

Summary: Test statistics for checking the independence between the innovations of several time series are developed. The time series models considered allow for general specifications for the conditional mean and variance functions that could depend on common explanatory variables. In testing for independence between more than two time series, checking pairwise independence does not lead to consistent procedures. Thus a finite family of empirical processes relying on multivariate lagged residuals are constructed, and we derive their asymptotic distributions. In order to obtain simple asymptotic covariance structures, Möbius transformations

•  Wikipedia
•  Wolfram MathWorld

of the empirical processes are studied, and simplifications occur. Under the null hypothesis

•  nLab
•  Wikipedia
•  Wolfram MathWorld

of independence, we show that these transformed processes are asymptotically Gaussian, independent, and with tractable covariance functions not depending on the estimated parameters. Various procedures are discussed, including Cramér-von Mises test statistics and tests based on nonparametric measures. The ranks of the residuals are considered in the new methods, giving test statistics which are asymptotically margin-free. Generalized cross-correlations are introduced, extending the concept of cross-correlation to an arbitrary number of time series; portmanteau procedures based on them are discussed. In order to detect the dependence visually, graphical devices are proposed. Simulations are conducted to explore the finite sample properties of the methodology, which is found to be powerful against various types of alternatives when the independence is tested between two and three time series. An application is considered, using the daily log-returns of Apple, Intel and Hewlett-Packard traded on the Nasdaq financial market.

MSC:

62M10	Time series, auto-correlation, regression, etc. in statistics (GARCH)
62M07	Non-Markovian processes: hypothesis testing
62G10	Nonparametric hypothesis testing
62G20	Asymptotic properties of nonparametric inference
62P05	Applications of statistics to actuarial sciences and financial mathematics

Keywords:

copula; Cramér-von Mises test statistic; cross-correlation; independence; Kolmogorov-Smirnov test statistic; multivariate lag; rank-based test statistic; time series

References:

[1]	Ansley, On the finite sample distribution of residual autocorrelations in autoregressive-moving average models, Biometrika 66 pp 547– (1979) · doi:10.1093/biomet/66.3.547
[2]	Bahadur, Stochastic comparison of tests, Annals of Mathematical Statistics 31 pp 276– (1960) · Zbl 0201.52203 · doi:10.1214/aoms/1177705894
[3]	Bai, Testing parametric conditional distributions of dynamic models, The Review of Economics and Statistics 85 pp 531– (2003) · doi:10.1162/003465303322369704
[4]	Bickel, Convergence criteria for multiparameter stochastic processes and some applications, Annals of Mathematical Statistics 42 pp 1656– (1971) · Zbl 0265.60011 · doi:10.1214/aoms/1177693164
[5]	Bougerol, Stationarity of GARCH processes and of some nonnegative time series, Journal of Econometrics 52 pp 115– (1992a) · Zbl 0746.62087 · doi:10.1016/0304-4076(92)90067-2
[6]	Bougerol, Strict stationarity of generalized autoregressive processes, Annals of Probability 20 pp 1714– (1992b) · Zbl 0763.60015 · doi:10.1214/aop/1176989526
[7]	Brockwell, Time Series: Theory and Methods (1991) · Zbl 0709.62080 · doi:10.1007/978-1-4419-0320-4
[8]	Brockwell, Introduction to Time Series and Forecasting (2002) · Zbl 0994.62085 · doi:10.1007/b97391
[9]	Carlstein, Nonparametric change-point estimation, The Annals of Statistics 16 pp 188– (1988) · Zbl 0637.62041 · doi:10.1214/aos/1176350699
[10]	Chen, Estimation and model selection of semiparametric copula-based multivariate dynamic models under copula misspecification, Journal of Econometrics 135 pp 125– (2006) · Zbl 1418.62425 · doi:10.1016/j.jeconom.2005.07.027
[11]	Deheuvels, La fonction de dépendance empirique et ses propriétés: Un test non paramétrique d’indépendance, Académie royale de Belgique, Bulletin de la classe des sciences, 5ième série 65 pp 274– (1979)
[12]	Deheuvels, Nonparametric Asymptotic Statistics (Proceedings of the Conference held in Rouen in 1979) pp 95– (1980)
[13]	Deheuvels, An asymptotic decomposition for multivariate distribution-free tests of independence, Journal of Multivariate Analysis 11 pp 102– (1981a) · Zbl 0486.62043 · doi:10.1016/0047-259X(81)90136-6
[14]	Deheuvels, A Kolmogorov-Smirnov type test for independence and multivariate samples, Revue roumaine de mathématiques pures et appliquées 26 pp 213– (1981b)
[15]	Deheuvels, A non parametric test for independence, Publications de l’Institut de statistique de l’Université de Paris 26 pp 29– (1981c)
[16]	Drouet-Mari, Correlation and Dependence (2001) · doi:10.1142/p226
[17]	Duchesne, Robust tests for independence of two time series, Statistica Sinica 13 pp 827– (2003) · Zbl 1029.62074
[18]	Fisher, Statistical Methods for Research Workers (1950) · JFM 64.0544.03
[19]	Francq, Maximum likelihood estimation of pure GARCH and ARMA-GARCH processes, Bernoulli 10 pp 605– (2004) · Zbl 1067.62094 · doi:10.3150/bj/1093265632
[20]	Francq, GARCH models: Structure, Statistical Inference and Financial Applications (2010) · doi:10.1002/9780470670057
[21]	Gänßler, Seminar on Empirical Processes (1987) · doi:10.1007/978-3-0348-6269-1
[22]	Genest, Rank-based extensions of the Brock Dechert Scheinkman test for serial dependence, Journal of the American Statistical Association 102 pp 1363– (2007) · Zbl 1332.62298 · doi:10.1198/016214507000001076
[23]	Genest, Estimators based on Kendall’s tau in multivariate copula models, Australian and New Zealand Journal of Statistics 53 pp 157– (2011) · Zbl 1274.62367 · doi:10.1111/j.1467-842X.2011.00622.x
[24]	Genest, Asymptotic local efficiency of Cramér-von Mises tests for multivariate independence, The Annals of Statistics 35 pp 166– (2007) · Zbl 1114.62058 · doi:10.1214/009053606000000984
[25]	Genest, Tests of independence or randomness based on the empirical copula process, Test 13 pp 335– (2004) · Zbl 1069.62039 · doi:10.1007/BF02595777
[26]	Genest, Omnibus goodness-of-fit tests for copulas: A review and a power study, Insurance: Mathematics & Economics 44 pp 199– (2009) · Zbl 1161.91416 · doi:10.1016/j.insmatheco.2007.10.005
[27]	Geweke, A comparison of tests of the independence of two covariance-stationary time series, Journal of the American Statistical Association 76 pp 363– (1981) · Zbl 0466.62083 · doi:10.1080/01621459.1981.10477655
[28]	Ghoudi, A nonparametric test of serial independence for time series and residuals, Journal of Multivariate Analysis 79 pp 191– (2001) · Zbl 1004.62043 · doi:10.1006/jmva.2000.1967
[29]	Ghoudi, Asymptotic Methods in Probability and Statistics (Ottawa, ON, 1997) pp 171– (1998) · doi:10.1016/B978-044450083-0/50012-5
[30]	Ghoudi, Asymptotic Methods in Stochastics pp 381– (2004) · doi:10.1090/fic/044/22
[31]	Granger, Modelling Non-linear Economic Relationships (1993) · Zbl 0893.90030
[32]	Hallin, Nonparametric tests of independence of two autoregressive time series based on autoregression rank scores, Journal of Statistical Planning and Inference 75 pp 319– (1999) · Zbl 0932.62057 · doi:10.1016/S0378-3758(98)00151-7
[33]	Hallin, New Directions in Time Series Analysis, Part I pp 111– (1992)
[34]	Hannan, The Statistical Theory of Linear Systems (1988) · Zbl 0641.93002
[35]	Haugh, Checking the independence of two covariance-stationary time series: a univariate residual cross-correlation approach, Journal of the American Statistical Association 71 pp 378– (1976) · Zbl 0337.62061 · doi:10.1080/01621459.1976.10480353
[36]	Hong, Testing for independence between two covariance stationary time series, Biometrika 83 pp 615– (1996) · Zbl 1029.62500 · doi:10.1093/biomet/83.3.615
[37]	Hong, Testing for pairwise serial independence via the empirical distribution function, Journal of the Royal Statistical Society, Series B 60 pp 429– (1998) · Zbl 0910.62046 · doi:10.1111/1467-9868.00134
[38]	Joe, Multivariate models and dependence concepts (1997) · Zbl 0990.62517 · doi:10.1201/b13150
[39]	Kim, A test for independence of two stationary infinite order autoregressive processes, Annals of the Institute of Statistical Mathematics 57 pp 105– (2005) · Zbl 1083.62090 · doi:10.1007/BF02506882
[40]	Klimko, On conditional least squares estimation for stochastic processes, The Annals of Statistics 6 pp 629– (1978) · Zbl 0383.62055 · doi:10.1214/aos/1176344207
[41]	Koch, A method for testing the independence of two time series that accounts for a potential pattern in the cross-correlation function, Journal of the American Statistical Association 81 pp 533– (1986) · Zbl 0604.62084 · doi:10.1080/01621459.1986.10478301
[42]	Lee, On residual empirical processes of stochastic regression models with applications to time series, The Annals of Statistics 27 pp 237– (1999) · Zbl 0943.62092 · doi:10.1214/aos/1018031109
[43]	Li, Diagnostic Checks in Time Series (2004) · Zbl 1053.62100
[44]	Li, Robust residual cross correlation tests for lagged relations in time series, Journal of Statistical Computation and Simulation 49 pp 103– (1994) · Zbl 0832.62080 · doi:10.1080/00949659408811563
[45]	Littell, Asymptotic optimality of Fisher’s method of combining independent tests. II, Journal of the American Statistical Association 68 pp 193– (1973) · Zbl 0259.62022 · doi:10.1080/01621459.1973.10481362
[46]	McLeod, On the distribution of residual autocorrelations in Box-Jenkins models, Journal of the Royal Statistical Society, Series B 40 pp 296– (1978) · Zbl 0407.62065
[47]	McLeod, Distribution of the residual cross-correlation in univariate ARMA time series models, Journal of the American Statistical Association 74 pp 849– (1979) · Zbl 0423.62069 · doi:10.1080/01621459.1979.10481041
[48]	Nelsen, An Introduction to Copulas (2006) · Zbl 1152.62030
[49]	Pierce, Relationships-and the lack thereof-between economic time series, with special reference to money and interest rates, Journal of the American Statistical Association 72 pp 11– (1977)
[50]	Potscher, Dynamic Nonlinear Econometric Models (1997) · doi:10.1007/978-3-662-03486-6
[51]	Reilly, Investment Analysis and Portfolio Management (2006)
[52]	Rémillard , B. 2010 Goodness-of-fit tests for copulas of multivariate time series
[53]	Romano, Counterexamples in Probability and Statistics (1986)
[54]	Rüschendorf, On the empirical process of multivariate, dependent random variables, Journal of Multivariate Analysis 4 pp 469– (1974) · Zbl 0292.60010 · doi:10.1016/0047-259X(74)90025-6
[55]	Rüschendorf, Asymptotic distributions of multivariate rank order statistics, The Annals of Statistics 4 pp 912– (1976) · Zbl 0359.62040 · doi:10.1214/aos/1176343588
[56]	Shao, A generalized portmanteau test for independence between two stationary time series, Econometric Theory 25 pp 195– (2009) · Zbl 1277.62198 · doi:10.1017/S0266466608090063
[57]	Skaug, A nonparametric test of serial independence based on the empirical distribution function, Biometrika 80 pp 591– (1993) · Zbl 0790.62044 · doi:10.1093/biomet/80.3.591
[58]	Spitzer, École d’Été de Probabilités de Saint-Flour, III-1973 pp 114– (1974)
[59]	Stute, The oscillation behavior of empirical processes: the multivariate case, The Annals of Probability 12 pp 361– (1984) · Zbl 0533.62037 · doi:10.1214/aop/1176993295
[60]	Taniguchi, Asymptotic Theory of Statistical Inference for Time Series (2000) · Zbl 0955.62088 · doi:10.1007/978-1-4612-1162-4
[61]	Tong, Non-linear Time Series: A Dynamical System Approach (1990) · Zbl 0716.62085
[62]	van der Vaart, Asymptotics: Particles, Processes and Inverse Problems pp 234– (2007) · Zbl 1176.62050 · doi:10.1214/074921707000000382