Linear and quadratic prediction problems in finite populations have become of great interest to many authors recently. In the present paper, we mainly aim to extend the problem of quadratic prediction from a general linear model, of form y=X@b+e,e~N(0,@s^2V), to a multivariate linear model, denoted by Y=XB+E,V ec(E)~N(0,@S@?V) with Y=(y"i"j)"n"x"q=(y"1,...,y"q). Firstly, the optimal invariant quadratic unbiased (OIQU) predictor and the optimal invariant quadratic (potentially) biased (OIQB) predictor of Y^'HY for any particular symmetric nonnegative definite matrix H satisfying HX=0 are derived. Secondly, we consider predicting a^'Y^'HYb and tr(Y^'HY). The corresponding restricted OIQU predictor and restricted OIQB predictor for them are given. In addition, we also offer four concluding remarks. One concerns the generalization of predicting a^'Y^'HYb and tr(Y^'HY), and the others are concerned with three possible extensions from multivariate linear models to growth curve models, to restricted multivariate linear models, and to matrix elliptical linear models.
[1]
Alan T. K. Wan,et al.
Improved multivariate prediction in a general linear model with an unknown error covariance matrix
,
2002
.
[2]
Jian-Ying Rong,et al.
Quadratic prediction problems in finite populations
,
2007
.
[3]
Heleno Bolfarine,et al.
Bayes and minimax prediction in finite populations
,
1991
.
[4]
Josemar Rodrigues,et al.
Robust Linear Prediction in Finite Populations
,
1983
.
[5]
Jian-Ying Rong,et al.
On quadratic prediction problems in finite populations
,
2008
.
[6]
S Yu.
OPTIMAL PREDICTION IN THE MULTIVARIATE LINEAR MODEL WITH ARBITRARY RANK
,
2001
.
[7]
K. Fang,et al.
Generalized Multivariate Analysis
,
1990
.
[8]
A. F. M. Smith,et al.
Prediction and Improved Estimation in Linear Models
,
1978
.