sigma_estim_ridge: Ridge-Penalized Covariance Estimation

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

Description

Computes the covariance matrix estimator with ridge-penalty.

Usage

sigma_estim_ridge(data, rho)

Arguments

data	an nxp data matrix.
rho	a double, indicating the ridge penalty.

Details

The ridge-penalized covariance matrix for a data matrix X is computed with the following formula:

\hat{Σ}=V≤ft(ρ C+(1-ρ)I\right)V,

where V is the sample volatility matrix, I is a pxp identity matrix, C is the sample correlation matrix and ρ is the user-sapplied ridge penalty parameter.

Value

a list with the following entries

• a pxp estimated covariance matrix.

• an estimation specific tuning parameter, here the user-supplied ridge penalty ρ.

References

\insertRef

warton2008penalizedCovEstim

Examples

data(sp200)
sp_rets <- sp200[,-1]
sigma_ridge <- sigma_estim_ridge(sp_rets, rho=0.01)[[1]]

antshi/CovEstim documentation built on Nov. 13, 2020, 2:25 p.m.