cv_bl function

Title

cv_bl(E, v_ord, N)

Arguments

• E: the observation matrix such that each of its row has a block structure correlation matrix Sigma to estimate up to a permutation of its columns and rows.
• v_ord: the absolute value of the upper triangular part matrix $\Gamma$ (including its diagonal) order in increasing order
• N: number of replication in the "cross-validation"

Returns

the number of non null values selected for the estimation of the covariance matrix

Details

In order to get the treshold one must do rev(v_ord)[cv_bl(E, v_ord, N=N)]

Examples

n <- 30
q <- 100
Sigma <- Simu_Sigma(q = q, diag = FALSE, equal = TRUE)
Matrix::image(Sigma)
E <- matrix(rnorm(n * q), ncol = q) %*% chol(as.matrix(Sigma))
k <- 5
v_up <- est_up(E, k = k)
a_vup <- abs(v_up)
ord_vup <- order(a_vup)
v_ord <- a_vup[ord_vup]
N <- 10
nb_nn0 <- cv_bl(E, v_ord, N=N)
tresh <- rev(v_ord)[nb_nn0]