Abstract
The inference of causal interaction structures in multivariate systems enables a deeper understanding of the investigated network. Analyzing nonlinear systems using partial directed coherence requires high model orders of the underlying vector-autoregressive process. We present a method to overcome the drawbacks caused by the high model orders. We calculate the corresponding statistics and provide a significance level. The performance is illustrated by means of model systems and in an application to neurological data.
| Original language | English |
|---|---|
| Article number | 051128 |
| Number of pages | 9 |
| Journal | Physical Review. E, Statistical, Nonlinear and Soft Matter Physics |
| Volume | 80 |
| Issue number | 5 |
| DOIs | |
| Publication status | Published - Nov 2009 |
Cite this
Estimating causal dependencies in networks of nonlinear stochastic dynamical systems. / Sommerlade, Linda; Eichler, Michael; Jachan, Michael; Henschel, Kathrin; Timmer, Jens; Schelter, Bjoern.
In: Physical Review. E, Statistical, Nonlinear and Soft Matter Physics, Vol. 80, No. 5, 051128, 11.2009.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Estimating causal dependencies in networks of nonlinear stochastic dynamical systems
AU - Sommerlade, Linda
AU - Eichler, Michael
AU - Jachan, Michael
AU - Henschel, Kathrin
AU - Timmer, Jens
AU - Schelter, Bjoern
PY - 2009/11
Y1 - 2009/11
N2 - The inference of causal interaction structures in multivariate systems enables a deeper understanding of the investigated network. Analyzing nonlinear systems using partial directed coherence requires high model orders of the underlying vector-autoregressive process. We present a method to overcome the drawbacks caused by the high model orders. We calculate the corresponding statistics and provide a significance level. The performance is illustrated by means of model systems and in an application to neurological data.
AB - The inference of causal interaction structures in multivariate systems enables a deeper understanding of the investigated network. Analyzing nonlinear systems using partial directed coherence requires high model orders of the underlying vector-autoregressive process. We present a method to overcome the drawbacks caused by the high model orders. We calculate the corresponding statistics and provide a significance level. The performance is illustrated by means of model systems and in an application to neurological data.
U2 - 10.1103/PhysRevE.80.051128
DO - 10.1103/PhysRevE.80.051128
M3 - Article
VL - 80
JO - Physical Review. E, Statistical, Nonlinear and Soft Matter Physics
JF - Physical Review. E, Statistical, Nonlinear and Soft Matter Physics
SN - 1539-3755
IS - 5
M1 - 051128
ER -