Minimum average variance estimation with group Lasso for the multivariate response central mean subspace (Q2034465)

This paper proposes a weighted version of the Minimum Average Variance Estimation (MAVE) method to estimate the Central Mean Subspace with multivariate response. The algorithm to implement the weighted MAVE method is provided. Asymptotic distribution of the MAVE estimator under the multivariate response setting is also derived. In addition, for the goal of variable selection, the adaptive group lasso regularization method is incorporated to induce sparse solutions. Experimental simulations and an application to real data are presented.