General constrained randomization

See the paper for an introduction to general constrained randomization of time series. This page describes an extendable family of routines for the generation of annealed surrogate data.

Current members of the family

Standard nonlinearity tests Nonlinearity test for unevenly sampled time series Nonlinearity test for event time sequences

Generic calling sequence

randomize_cost_cool_perm [-n# -u# -I# -o outfile -l# -x# -c#[,#] -m# -V# -h]
cost function options] [cooling options] [permutation options] file

-n number of surrogates (default 1)
-u improvement factor before write (default 0.9 = if 10% better)
-I seed for random numbers (0)
-l maximal number of points to be processed (default all)
-x number of values to be skipped (0)
-c columns to be read (1 or file,#)
-m number of components (ignored for scalar data)
-o output file name, just -o means file_rnd(_nnn)
-V verbosity level (0 = only fatal errors)
-h show usage message

verbosity level (add what you want):

1 = input/output
2 = current value of cost function upon printable improvement
4 = cost mismatch
8 = temperature etc. at cooling
16 = verbose cost if improved
32 = verbose cost mismatch

The variables cost, cool, and perm expand to one of the implemented cost functions, cooling schemes, and permutation schemes. Each of these may have their specific options which are described under each module. In general, a one-column file is read and the values are permuted randomly under certain constraints. These constraints are usually (but not necessarily) derived from the data and implemented in the form of a cost function which is minimized by the method of simulated annealing.

Output is written to file_rnd_nnn, n=1...number, also at intermediate stages specified by -u.

This family of routines is based on

T. Schreiber
Constrained randomization of time series data
Phys. Rev. Lett. 80, 2105 (1998).

Table of Contents * TISEAN home