SiZer for time series: A new approach to the analysis of trends

Smoothing methods and SiZer are a useful statistical tool for discovering statistically significant structure in data. Based on scale space ideas originally developed in the computer vision literature, SiZer (SIgnificant ZERo crossing of the derivatives) is a graphical device to assess which observed features are `really there' and which are just spurious sampling artifacts. In this paper, we develop SiZer like ideas in time series analysis to address the important issue of significance of trends. This is not a straightforward extension, since one data set does not contain the information needed to distinguish `trend' from `dependence'. A new visualization is proposed, which shows the statistician the range of trade-offs that are available. Simulation and real data results illustrate the effectiveness of the method.

[1]  Shean-Tsong Chiu,et al.  Bandwidth selection for kernel estimate with correlated noise , 1989 .

[2]  Tony Lindeberg,et al.  Scale-Space Theory in Computer Vision , 1993, Lecture Notes in Computer Science.

[3]  H. Müller,et al.  Local Polynomial Modeling and Its Applications , 1998 .

[4]  Naomi Altman,et al.  Kernel Smoothing of Data with Correlated Errors , 1990 .

[5]  Irène Gijbels,et al.  Understanding exponential smoothing via kernel regression , 1999 .

[6]  A. Bowman,et al.  Applied smoothing techniques for data analysis : the kernel approach with S-plus illustrations , 1999 .

[7]  James Stephen Marron,et al.  Presentation of smoothers: the family approach , 2001, Comput. Stat..

[8]  Tony Lindeberg,et al.  Scale-space theory , 2001 .

[9]  Jeffrey D. Hart,et al.  Nonparametric Smoothing and Lack-Of-Fit Tests , 1997 .

[10]  J. Simonoff.  Smoothing Methods in Statistics , 1998 .

[11]  Yuhong Yang,et al.  Nonparametric Regression with Correlated Errors , 2001 .

[12]  Richard A. Davis,et al.  Time Series: Theory and Methods (2nd ed.). , 1992 .

[13]  Jan Mielniczuk,et al.  Nonparametric Regression Under Long-Range Dependent Normal Errors , 1995 .

[14]  Richard A. Davis,et al.  Time Series: Theory and Methods , 2013 .

[15]  J. Marron,et al.  Comparison of Two Bandwidth Selectors with Dependent Errors , 1991 .

[16]  James Stephen Marron,et al.  Dependent SiZer: Goodness-of-Fit Tests for Time Series Models , 2004 .

[17]  J. Marron,et al.  SiZer for Exploration of Structures in Curves , 1999 .

[18]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .

[19]  Matthew P. Wand,et al.  Kernel Smoothing , 1995 .

[20]  James Stephen Marron,et al.  Significance of Features via SiZer , 1998 .

[21]  T. Gasser,et al.  Choice of bandwidth for kernel regression when residuals are correlated , 1992 .

[22]  B. Silverman,et al.  Nonparametric regression and generalized linear models , 1994 .

[23]  J. Hart.  Kernel regression estimation with time series errors , 1991 .

[24]  S. Lahiri,et al.  On bandwidth choice in nonparametric regression with both short- and long-range dependent errors , 1995 .