Estimating Predictability: Redundancy and Surrogate Data Method

A method for estimating theoretical predictability of time series is presented, based on information-theoretic functionals---redundancies and surrogate data technique. The redundancy, designed for a chosen model and a prediction horizon, evaluates amount of information between a model input (e.g., lagged versions of the series) and a model output (i.e., a series lagged by the prediction horizon from the model input) in number of bits. This value, however, is influenced by a method and precision of redundancy estimation and therefore it is (a) normalized by maximum possible redundancy (given by the precision used), and (b) compared to the redundancies obtained from two types of the surrogate data in order to obtain reliable classification of a series as either unpredictable or predictable. The type of predictability (linear or nonlinear) and its level can be further evaluated. The method is demonstrated using a numerically generated time series as well as high-frequency foreigh exchange data and the theoretical predictability is compared to performance of a nonlinear predictor.

[1]  D. A. Bell,et al.  Information Theory and Reliable Communication , 1969 .

[2]  G. Hommel.  Tests of the overall hypothesis for arbitrary dependence structures , 1983 .

[3]  M. Paluš.  Detecting Nonlinearity in Multivariate Time Series , 1996 .

[4]  James Theiler,et al.  Testing for nonlinearity in time series: the method of surrogate data , 1992 .

[5]  Theiler,et al.  Generating surrogate data for time series with several simultaneously measured variables. , 1994, Physical review letters.

[6]  M. Paluš,et al.  Information theoretic test for nonlinearity in time series , 1993 .

[7]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[8]  Milan PALUS.  Testing For Nonlinearity Using Redundancies: Quantitative and Qualitative Aspects , 1994 .

[9]  D. G. Watts,et al.  Spectral analysis and its applications , 1968 .

[10]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[11]  James Theiler,et al.  Constrained-realization Monte-carlo Method for Hypothesis Testing , 1996 .

[12]  D. B. Preston.  Spectral Analysis and Time Series , 1983 .

[13]  B. Efron.  The jackknife, the bootstrap, and other resampling plans , 1987 .

[14]  Milan Paluš,et al.  Testing for Nonlinearity in Weather Records , 1994 .

[15]  John W. Tukey,et al.  Data Analysis and Regression: A Second Course in Statistics , 1977 .

[16]  D. Morgenstern,et al.  Berechnung des maximalen Signifikanzniveaus des Testes „LehneH0 ab, wennk untern gegebenen Tests zur Ablehnung führen” , 1980 .

[17]  James Theiler,et al.  Using surrogate data to detect nonlinearity in time series , 1991 .

[18]  M. Dacorogna,et al.  A geographical model for the daily and weekly seasonal volatility in the foreign exchange market , 1993 .

[19]  Aleksandr Yakovlevich Khinchin,et al.  Mathematical foundations of information theory , 1959 .