sigma_estim_poet: Principal Orthogonal ComplEment Thresholding (POET)...
In antshi/CovEstim: (High-dimensional) Covariance Estimation

Description Usage Arguments Details Value References Examples

Computes the POET estimator of the covariance matrix.

1	sigma_estim_poet(data, K = NULL, C = 1, thres = "soft", matrix = "vad")

`data`	an nxp data matrix.
`K`	an integer, the number of principal components (factors). Default values is NULL and the optimal K is calculated as in \insertCitepoetpackage;textualCovEstim. K=0 corresponds to threshoding the sample covariance directly.
`C`	a double, the positive constant for thresholding. Default value is 1.
`thres`	a character, indicating the choice of thresholding. Possible values are "soft" for soft-thresholding, "hard" for hard thresholding and "scad" for scad thresholding. Default is "soft".
`matrix`	a character, indicating the option of thresholding either correlation or covairance matrix. Possible values are "cor" for thresholding the error correlation matrix then transform back to covariance matrix and "vad" for thresholding the error covariance matrix directly. Default is "cor".

The POET estimator of the covariance matrix is computed according to \insertCitefan2013poet;textualCovEstim. The POET estimation is originally found under \insertCitepoetpackage;textualCovEstim.

a list with the following entries

a pxp estimated covariance matrix.
an estimation specific tuning parameter, here the number of principal components K.

\insertAllCited

data(sp200)
sp_rets <- sp200[,-1]
sigma_poet <- sigma_estim_poet(sp_rets, K=2)[[1]] # user-defined K
sigma_poet <- sigma_estim_poet(sp_rets)[[1]] # optimal K