Generate the matrices of S-map coefficients

Using the S-map coefficients, assemble the appropriate Jacobian matrices for each time point

compute_smap_matrices(smap_coeffs, ccm_links)

Arguments

smap_coeffs	A list of the S-map coefficients for each predictor variable (as returned from compute_smap_coeffs())
ccm_links	A data.frame containing the significant causal links. Each row is a causal link. The columns are: xmap_from the column index of the predictor variable in CCM xmap_to the column index of the predicted variable in CCM best_E the best embedding dimension for CCM

Value

A list with the matrix of smap-coefficients at each time point

Details

See compute_smap_coeffs() for details on the input data. Let the variables in the system be x^i with i = 1..N. For the S-map model predicting x^it+1, let the coefficient corresponding to variable x^j at lag tau be c^tauij. Then the Jacobian is the block matrix, J =

	C^0	C^1	...	C^(d-1)
C^d		I	0	...
0	0		0	I
...	0	0		...
...	...	...	...
0	0	...	I	0

where d is the maximum lag, and C^tau is the matrix formed by the values c^tau_ij. (Note that many of these values will be 0.)

This function computes J at each time step.