Hi Amir,

Excerpts from http://www.fil.ion.ucl.ac.uk/~wpenny/publications/integration.pdf :

"...SEMs comprise a set of regions and a set of directed connections. A causal semantics is ascribed to these connections where an arrow from A to B means that A causes B. Causal relationships are thus not inferred from the data but are assumed a priori...".

In DCM, "...Experimental inputs cause changes in effective connectivity expressed at the level of neurodynamics, which in turn cause changes in the observed hemodynamics..."

Some related references:

• About DCM - Friston et al., "Dynamic causal modelling", 2003: http://www.fil.ion.ucl.ac.uk/~karl/Dynamic%20causal%20modelling.pdf
• About SEM - McIntosh et al., "Structural Equation Modeling and Its Application to Network Analysis in Functional Brain Imaging", 1994: http://booksc.org/dl/1329691/1fc2c4
• Comparison between SEM and DCM - Penny et al., "Modelling functional integration: a comparison of structural equation and dynamic causal models", 2004: http://www.fil.ion.ucl.ac.uk/~wpenny/publications/integration.pdf

Finally, another reference that may be of interest to help you in solving your problem: Kawahara et al., "Analyzing relationships among ARMA processes based on non-Gaussianity of external influences", 2011 ( http://booksc.org/dl/3771886/6ebf5e )

Choosing an appropriate method depends mainly on how you perceive the problem. Is the problem more a matter of time series prediction or dynamic system modeling? Or both of them?

Regards

A bit late to the party, nevertheless, just learnt about SEM so am going to say SD given I did something like that in my doctoral project

I developed a SD model of the automotive recycling industry in Australia using stakeholder interview data and qualitative data from industry reports. The qualitative model was then further developed into a quantitative/simulation SD model that served as basis for analysing policy options (emerged from a scenario planning workshop with a group of stakeholders).

Curious to know what you eventually went with?

Here is the link to my thesis.

https://openresearch-repository.anu.edu.au/handle/1885/164194

Regards