Testing chaotic dynamics via Lyapunov exponents
References (2)
A statistical framework for testing chaotic dynamics via Lyapunov exponents
Physica D
(1996)- et al.
Moving blocks Jackknife and bootstrap capture weak dependence
Cited by (27)
Chaos measure dynamics in a multifactor model for financial market predictions
2024, Communications in Nonlinear Science and Numerical SimulationHurst exponent dynamics of S&P 500 returns: Implications for market efficiency, long memory, multifractality and financial crises predictability by application of a nonlinear dynamics analysis framework
2023, Chaos, Solitons and FractalsCitation Excerpt :Thus, we calculate the DFA alpha instead of the Hurst exponent of our data, as DFA can cope with non-stationary data [52]. To conclude, we calculate a significance test for the Hurst exponent dynamics analogue to Bask and Gençay [85]. Therefore, we apply 50,0008 bootstrapping steps via a shuffling procedure (refer to [86]) to determine whether the Hurst exponents are significant (1) per respective window as data basis and (2) with regard to the complete data series as data basis.
Chaoticity versus stochasticity in financial markets: Are daily S&P 500 return dynamics chaotic?
2022, Communications in Nonlinear Science and Numerical SimulationCitation Excerpt :Therefore, as indicated by Gençay [78], a methodology to compute empirical distributions of Lyapunov exponents via a blockwise bootstrap technique is a formal test of the hypothesis that the Lyapunov exponent reflects chaotic dynamics [79]. In particular, the test proposed by Gençay [78] can be applied to Lyapunov exponents, which are slightly above zero within a small sample [80]. Because we were studying such a dataset8 we applied this approach for our empirical analysis.
Partial chaos suppression in a fractional order macroeconomic model
2016, Mathematics and Computers in SimulationNonlinear multiscale Maximal Lyapunov Exponent for accurate myoelectric signal classification
2015, Applied Soft Computing JournalCitation Excerpt :LLE has high sensitivity to initial conditions and noise, whereas WLE, RLE and KLE are not easily affected by topology complexity and have certain anti-interference ability. However, WLE is susceptible to multi-parameter situations and requires a long data length [10]. Moreover, none of the above mentioned MLE methods can recognize the multiscale characteristic of fractional Brownian motion [3].
Measuring potential market risk
2010, Journal of Financial Stability
- 1
Tel.: +1-519-253 4232; fax: +1-519-973 7096