scientific article; zbMATH DE number 1383054

From MaRDI portal
Publication:4718909





The following growth curver model is considered: \[ Y=X_1 BX_2+ \varepsilon, \quad E(\varepsilon)= 0\text{ cov} (\vec\varepsilon) =\sigma^2 I_q \otimes \Sigma,\tag{1} \] where \(X_1,X_2\) and \(\Sigma >0\) are \(n\times p\), \(k \times q\) and \(n\times n\) known matrices, respectively. The author considers the minimax admissibility characterization of linear estimates of multivariate regression coefficients for (1), and gives necessary and sufficient conditions for a linear estimator DYF (DYF+H) to be minimax admissible among the class of homogeneous (nonhomogeneous) linear estimators.











This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4718909)