Evaluation.GGMM: Evaluation function for the estimated Gaussian graphical...

In TransGraph: Transfer Graph Learning

Evaluation function for the estimated Gaussian graphical mixture models.

Description

Evaluation function for the estimated Gaussian graphical mixture models.

Usage

Evaluation.GGMM(data, mu_hat, Theta_hat, Mu0, Theta0, M0, L.mat, L0, prob)

Arguments

data	The target data, a n * p matrix, where n is the sample size and p is data dimension.
mu_hat	M0_hat * p matrix, the estimated mean vectors of M0_hat subgroups.
Theta_hat	p * p * M0_hat array, the estimated precision matrices of M0_hat subgroups.
Mu0	M0 * p matrix, the true mean vectors of M0 subgroups.
Theta0	p * p * M0 array, the true precision matrices of M0 subgroups.
M0	The true number of subgroups
L.mat	The estimated clustering results.
L0	The true clustering results.
prob	The estimated subgroup proportion.

Value

The vector including: K: The estimated number of subgroups. CE: The sub-grouping error CME: The mean squared error (MSE) for the mean vectors. PME: The mean squared error (MSE) for the precision matrices. TPR/FPR: The true and false positive rates for the off-diagonal elements of the precision matrices.

Author(s)

Mingyang Ren [e-mail].

References

Ren, M., Zhang S., Zhang Q. and Ma S. (2020). Gaussian Graphical Model-based Heterogeneity Analysis via Penalized Fusion. Biometrics.

TransGraph documentation built on Nov. 12, 2025, 9:06 a.m.