Non-linear time series clustering based on non-parametric forecast densities

The problem of clustering time series is studied for a general class of non-parametric autoregressive models. The dissimilarity between two time series is based on comparing their full forecast densities at a given horizon. In particular, two functional distances are considered: L^1 and L^2. As the forecast densities are unknown, they are approximated using a bootstrap procedure that mimics the underlying generating processes without assuming any parametric model for the true autoregressive structure of the series. The estimated forecast densities are then used to construct the dissimilarity matrix and hence to perform clustering. Asymptotic properties of the proposed method are provided and an extensive simulation study is carried out. The results show the good behavior of the procedure for a wide variety of nonlinear autoregressive models and its robustness to non-Gaussian innovations. Finally, the proposed methodology is applied to a real dataset involving economic time series.

[1]  Wenceslao González-Manteiga,et al.  Saving computer time in constructing consistent bootstrap prediction intervals for autoregressive processes , 1997 .

[2]  L. Devroye,et al.  Nonparametric Density Estimation: The L 1 View. , 1985 .

[3]  P. Vieu.  Order Choice in Nonlinear Autoregressive Models , 1995 .

[4]  Edoardo Otranto,et al.  Clustering heteroskedastic time series by model-based procedures , 2008, Comput. Stat. Data Anal..

[5]  Ahlame Douzal Chouakria,et al.  Adaptive dissimilarity index for measuring time series proximity , 2007, Adv. Data Anal. Classif..

[6]  E. Mammen,et al.  Bootstrap of kernel smoothing in nonlinear time series , 2002 .

[7]  Elizabeth Ann Maharaj,et al.  A SIGNIFICANCE TEST FOR CLASSIFYING ARMA MODELS , 1996 .

[8]  Marcella Corduas,et al.  Time series clustering and classification by the autoregressive metric , 2008, Comput. Stat. Data Anal..

[9]  Francesco Giordano,et al.  Forecasting nonlinear time series with neural network sieve bootstrap , 2007, Comput. Stat. Data Anal..

[10]  José A. Vilar,et al.  Discriminant and cluster analysis for Gaussian stationary processes: local linear fitting approach , 2004 .

[11]  H. Tong.  Non-linear time series. A dynamical system approach , 1990 .

[12]  Timo Teräsvirta,et al.  Testing linearity in univariate, time series models , 1988 .

[13]  Salvatore Grimaldi,et al.  Linear Parametric Models Applied to Hydrological Series , 2004 .

[14]  Ahlame Douzal Chouakria,et al.  Adaptive clustering for time series: Application for identifying cell cycle expressed genes , 2009, Comput. Stat. Data Anal..

[15]  Jeffrey D. Hart,et al.  Automated Kernel Smoothing of Dependent Data by Using Time Series Cross‐Validation , 1994 .

[16]  Lijian Yang,et al.  Nonparametric Lag Selection for Time Series , 2000 .

[17]  T. P. Hettmansperger,et al.  Data-based bandwidth selection for kernel estimators of the integral of f2(x) , 1994 .

[18]  Tomasz Rychlik,et al.  Bounds for expectation of l-estimates for dependent samples , 1993 .

[19]  D. Piccolo.  A DISTANCE MEASURE FOR CLASSIFYING ARIMA MODELS , 1990 .

[20]  Qiwei Yao,et al.  On subset selection in non-parametric stochastic regression , 1994 .

[21]  Jorge Caiado,et al.  A periodogram-based metric for time series classification , 2006, Comput. Stat. Data Anal..

[22]  Dag Tjøstheim,et al.  Nonparametric Identification of Nonlinear Time Series: Selecting Significant Lags , 1994 .

[23]  Matteo Grigoletto,et al.  Bootstrap prediction intervals for autoregressions: some alternatives , 1998 .

[24]  M. C. Jones,et al.  A reliable data-based bandwidth selection method for kernel density estimation , 1991 .

[25]  Mike Dale,et al.  Building Models of Ecological Dynamics Using HMM Based Temporal Data Clustering - A Preliminary Study , 2001, IDA.

[26]  T. Warren Liao,et al.  Clustering of time series data - a survey , 2005, Pattern Recognit..

[27]  Robert H. Shumway,et al.  Discrimination and Clustering for Multivariate Time Series , 1998 .

[28]  Denis Bosq,et al.  Nonparametric statistics for stochastic processes , 1996 .

[29]  A. I. McLeod,et al.  DIAGNOSTIC CHECKING ARMA TIME SERIES MODELS USING SQUARED‐RESIDUAL AUTOCORRELATIONS , 1983 .

[30]  柿沢 佳秀,et al.  Asymptotic theory of statistical inference for time series , 2000 .