Abstract
The validity of a heuristic segmentation algorithm was studied by analyzing surrogate time series with different statistical properties. The algorithm can split the time series into a set of stationary segments with correct statistical properties, if a given nonstationary time series has stationary periods whose length is distributed as a power law. It also cuts time series into the stationary segments if there are long-range temporal correlations of the fluctuations around the mean of the segment. The results suggest that one must calculate the ratio between the standard deviation of the mean value of the segment and the standard deviation of the fluctuations within a segment after performing the segmentation.
| Original language | English (US) |
|---|---|
| Article number | 021108 |
| Pages (from-to) | 021108-1-021108-12 |
| Journal | Physical Review E - Statistical, Nonlinear, and Soft Matter Physics |
| Volume | 69 |
| Issue number | 2 1 |
| DOIs | |
| State | Published - Feb 2004 |
ASJC Scopus subject areas
- Condensed Matter Physics
- Statistical and Nonlinear Physics
- Statistics and Probability