Estimation of high-dimensional seemingly unrelated regression models

In this paper, we investigate seemingly unrelated regression (SUR) models that allow the number of equations (N) to be large, and comparable observations in each equation (T). It is well known literature conventional SUR estimator, for example, generalized least squares (GLS) estimator Zellner (1962) does not perform well. As main contribution propose a new feasible GLS called graphical lasso (FGLasso) estimator. For implementation use estimation precision matrix (the inverse covariance system errors) assuming underlying unknown sparse. We derive asymptotic theories its finite sample properties via Monte-Carlo simulations.