Using missing ordinal patterns to detect nonlinearity in time series data

OSBORNE, THOMAS; ZAWADZKI, BRIANNA; KULP, CHRISTOPHER W.; ZUNINO, LUCIANO

Physical Review E

American Physical Society

Año: 2017 vol. 96 p. 22218 - 22218

2470-0045

The number of missing ordinal patterns (NMP) is the number of ordinal patterns that do not appear in a series after it has been symbolized using the Bandt and Pompe methodology. In this paper, the NMP is demonstrated as a test for nonlinearity using a surrogate framework in order to see if the NMP for a series is statistically different from the NMP of iterative amplitude adjusted Fourier transform (IAAFT) surrogates. It is found that the NMP works well as a test statistic for nonlinearity, even in the cases of very short time series. Both model and experimental time series are used to demonstrate the efficacy of the NMP as a test for nonlinearity.