CONNECTIVITYLIB::MvarModel Class Reference

MVAR model fit; provides H(f) and S(f) for Granger Causality, DTF and PDC. More...

#include <mvar_model.h>

Public Member Functions
	MvarModel ()=default
void	fit (const Eigen::MatrixXd &data, int p=0)
QVector< Eigen::MatrixXd >	coefficients () const
Eigen::MatrixXd	noiseCov () const
int	order () const
QVector< Eigen::MatrixXcd >	transferFunction (const Eigen::VectorXd &freqs) const
QVector< Eigen::MatrixXcd >	spectralMatrix (const Eigen::VectorXd &freqs) const

Detailed Description

MVAR model fit; provides H(f) and S(f) for Granger Causality, DTF and PDC.

Multivariate autoregressive (MVAR) model fit and its frequency-domain decomposition into transfer function H(f) and spectral matrix S(f).

The model order p is either supplied by the caller or selected automatically by Bayesian Information Criterion over [1, 20]; the coefficient matrices are estimated by Levinson-Durbin recursion on the Yule-Walker equations. The resulting H and S are consumed by the three directed-connectivity metrics in this library (Granger Causality, DTF, PDC) and are exposed via transferFunction and spectralMatrix at arbitrary normalised frequencies.

Since

2.2.0

Definition at line 88 of file mvar_model.h.

Constructor & Destructor Documentation

MvarModel()

CONNECTIVITYLIB::MvarModel::MvarModel ( )

default

Constructs a default MvarModel object.

Member Function Documentation

coefficients()

QVector< MatrixXd > MvarModel::coefficients

(

)

const

Returns the fitted coefficient matrices A_1 .. A_p (each nChannels x nChannels).

Returns

The MVAR coefficient matrices.

Since

2.2.0

Definition at line 60 of file mvar_model.cpp.

fit()

void MvarModel::fit	(	const Eigen::MatrixXd &	data,
		int	p = 0 )

Fits an MVAR model of order p to multi-channel data.

Parameters

[in]	data	The input data matrix (nChannels x nSamples).
[in]	p	The model order. If 0, the order is auto-selected via BIC.

Since

2.2.0

Definition at line 47 of file mvar_model.cpp.

noiseCov()

MatrixXd MvarModel::noiseCov

(

)

const

Returns the noise covariance matrix (nChannels x nChannels).

Returns

The noise covariance matrix.

Since

2.2.0

Definition at line 67 of file mvar_model.cpp.

order()

int MvarModel::order

(

)

const

Returns the fitted model order.

Returns

The model order p.

Since

2.2.0

Definition at line 74 of file mvar_model.cpp.

spectralMatrix()

QVector< MatrixXcd > MvarModel::spectralMatrix

(

const Eigen::VectorXd &

freqs

)

const

Computes the spectral matrix S(f) = H(f) * Sigma * H(f)^H.

Parameters

[in]

freqs

Vector of normalized frequencies in [0, 0.5].

Returns

Vector of nChannels x nChannels complex matrices, one per frequency.

Since

2.2.0

Definition at line 107 of file mvar_model.cpp.

transferFunction()

QVector< MatrixXcd > MvarModel::transferFunction

(

const Eigen::VectorXd &

freqs

)

const

Computes the transfer function H(f) at the given normalized frequencies.

H(f) = (I - sum_{k=1}^{p} A_k * exp(-2*pi*i*f*k))^{-1}

Parameters

[in]

freqs

Vector of normalized frequencies in [0, 0.5].

Returns

Vector of nChannels x nChannels complex matrices, one per frequency.

Since

2.2.0

Definition at line 81 of file mvar_model.cpp.

---

The documentation for this class was generated from the following files:

• src/libraries/connectivity/metrics/mvar_model.h
• src/libraries/connectivity/metrics/mvar_model.cpp