cov_estim_pca: Principal Component Analysis Covariance Estimation

In antshi/CovEstim: (High-dimensional) Covariance Estimation

Principal Component Analysis Covariance Estimation

Description

Computes a Principal Component Analysis (PCA) estimator of the covariance matrix.

Usage

cov_estim_pca(data, number_pc = NULL)

Arguments

data	an nxp data matrix
number_pc	an integer, indicating the number of principal components. Default value is NULL and the number of principal components is set according to the Marcenko-Pastur edge as in \insertCitemarvcenko1967distribution;textualcovestim.

Value

a list with the following entries

• a pxp estimated covariance matrix.

• an estimation specific tuning parameter, here the number of principal components.

References

\insertRef

johnson2002appliedcovestim

\insertRef

fan2016overviewcovestim

Examples

data(rets_m)
# user-defined number of factors
sigma_pca <- cov_estim_pca(rets_m, number_pc = 2)[[1]]
# number of factors, defined with MP cut-edge
results_pca_mp <- cov_estim_pca(rets_m)
sigma_pca_mp <- results_pca_mp[[1]]
number_pc <- results_pca_mp[[2]]

antshi/CovEstim documentation built on June 10, 2025, 3:11 a.m.