We study the problem of classi¯cation for multivariate repeated measures data with struc- tured correlations on both time and spatial repeated measurements. This is a very important problem in many biomedical as well as in engineering ¯eld. Classi¯cation rules as well as the algorithm to...

The paper deals with an heuristic generalization of the traditional classication rules by incorporating within sample dependencies. The main motivation behind this generalization is to develop a new classication rule when training samples are not random, but, jointly equicorrelated.

We study the general linear model (GLM) with doubly exchangeable distributed error for m observed random variables. The doubly exchangeable linear model (DEGLM) arises when the m¡dimensional error vectors are \doubly exchangeable" (de¯ned later), jointly normally distributed, which is much...

This paper considers the problem of estimating, and testing for, a Kronecker product covariance structure of three-level (multiple time points (p), multiple sites (u), and multiple response variables (q)) multivariate data. Testing of such covariance structures is potentially important when not...