Generate a banding operator with given dimention and tuning parameter. Multiplying it on a covariance matrix by componentwise product can provide a regularized estimator with the banding method.
banding(p, k = 1)
the dimension of a covariance matrix.
the default value is 1.
Bickel, P and Levina, E, Regularized estimation of large covariance matrices, Annals of Statistics, 36, 199-227 (2008).
1 2 3
p <- 5; W <- banding(p,k=2) ; W;
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.