Permutation entropy provides a simple and robust method to estimate
complexity of time series, taking the temporal order of the values
into account.
Furthermore, permutation entropy can be used to determine embedding
parameters or identify couplings between time series. For further
instructions please consider the reference given below.
Usage
H = petropy(x,n,tau,method,accu)
x
time series (N × 1 or 1 × N vector)
n
permutation order
tau
time lag/ time lag vector (length = n-1)
method
method how to deal with equal values in the series 'noise' - add small noise to the values in x 'same' - allow same rank for equal values 'order' - consider order of appearance (first occurence --> lower rank)
accu
maximum number of decimal places in x (only used for method 'noise')
H gives the value of the permutation entropy according
to H = − ∑(pj log2 pj) (j = 1, …, n).
Example
Consider the time series
x = [6,9,11,12,8,13,5];
The permutation entropy of this time series with a permutation
order of 3 and with lag 1 is
H = petropy(x,3,1,'order');
H =
1.5219
References
Riedl, M., Müller, A., Wessel, N.:
Practical considerations of permutation entropy,
Eur. Phys. J. ST, 222(2), 249-262, 2013.
