AN INVESTIGATION OF THE ABILITY OF NONLINEAR METHODS TO INFER DYNAMICS FROM OBSERVABLES

In this study analysis of data whose character was kept secret was per formed by employing a variety of nonlinear approaches. The idea was to test the ability of approaches stemming from the the theory of nonlin ear dynamical systems to infer the true properties hidden in the data. The approaches employed include dimension estimation, nonlinear predi ction, Lyapunov exponent estimation, and false nearest neighbors. It i s concluded that even though the methods have problems and occasionall y may be inconclusive, when correctly applied they are effective in de lineating the dynamics underlying the data.