Additivity tests for nonlinear autoregression

SUMMARY Additivity is commonly used in the statistical literature to simplify data analysis, especially in analysis of variance and in multivariate smoothing. In this paper, we propose three procedures for testing additivity in nonlinear time series analysis. The first procedure combines some smoothing techniques with analysis of variance, the second is a Lagrange multiplier test using nonparametric estimation, and the third is a permutation test which uses smoothing techniques to obtain the test statistic and its reference distribution. We investigate properties of the proposed tests and use simulation to check their performance in finite samples. Applications of the tests to nonlinear time series analysis are discussed and illustrated by real examples.

[1]  R. Tibshirani.  Estimating Transformations for Regression via Additivity and Variance Stabilization , 1988 .

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

[3]  Hung Man Tong,et al.  Threshold models in non-linear time series analysis. Lecture notes in statistics, No.21 , 1983 .

[4]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[5]  T. Rao,et al.  An Introduction to Bispectral Analysis and Bilinear Time Series Models , 1984 .

[6]  R. Tsay.  Nonlinearity tests for time series , 1986 .

[7]  Ker-Chau Li.  Sliced inverse regression for dimension reduction (with discussion) , 1991 .

[8]  M. B. Priestley,et al.  Non-linear and non-stationary time series analysis , 1990 .

[9]  J. Friedman,et al.  Projection Pursuit Regression , 1981 .

[10]  T. Ozaki,et al.  Modelling nonlinear random vibrations using an amplitude-dependent autoregressive time series model , 1981 .

[11]  David Roxbee Cox,et al.  Nonlinear autoregressive processes , 1978, Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences.

[12]  J. Friedman,et al.  Estimating Optimal Transformations for Multiple Regression and Correlation. , 1985 .

[13]  D. M. Keenan,et al.  A Tukey nonadditivity-type test for time series nonlinearity , 1985 .

[14]  J. Tukey.  One Degree of Freedom for Non-Additivity , 1949 .

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

[16]  P. Lewis,et al.  Nonlinear Modeling of Time Series Using Multivariate Adaptive Regression Splines (MARS) , 1991 .

[17]  Peter A. W. Lewis,et al.  NONLINEAR MODELING OF MULTIVARIATE AND CATEGORICAL TIME SERIES USING MULTIVARIATE ADAPTIVE REGRESSION SPLINES , 1993 .

[18]  C. Granger,et al.  An introduction to bilinear time series models , 1979 .

[19]  R. Tibshirani,et al.  Generalized Additive Models , 1991 .

[20]  R. A. Koyak.  Consistency for ACE-Type Methods , 1990 .

[21]  Ruey S. Tsay,et al.  Nonlinear Additive ARX Models , 1993 .

[22]  Ruey S. Tsay,et al.  Functional-Coefficient Autoregressive Models , 1993 .

[23]  R. Tibshirani,et al.  Generalized additive models for medical research , 1986, Statistical methods in medical research.

[24]  D. Tjøstheim,et al.  Identification of nonlinear time series: First order characterization and order determination , 1990 .