Milan Palus
Institute of Computer Science,
Academy of Sciences of the Czech Republic
Pod vodárenskou vezí 2,
182 07 Prague 8, Czech Republic
E-mail: mp@uivt.cas.cz, mp@santafe.edu
In this chapter we briefly review a method for detection and characterization of nonlinear relations in multivariate as well as in univariate time series. The method employs the technique of uni- and multivariate surrogate data and information-theoretic functionals called redundancies. The test for nonlinearity based on the redundancy -- linear redundancy approach, combined with the surrogate data is described in detail in (Palus 1995), its multivariate version in (Palus 1996). The univariate surrogate data have been introduced in (Theiler et al 1992), and the multivariate surrogate data in (Pritchard & Theiler 1994).