If Yi is used to indicate the ni x 1 vector of outcomes for individual i, then let vi be the vector of variances for these effects. Ai is a diagonal matrix that has taken on the values of the vector vi. Let α represent the correlation within the clustered measurements then Ri (α) is the working correlation matrix for these same quantities. In this study, it is assumed that there is a correlation structure Ri (α) common to all subjects. If Ai is an ni × ni matrix with the variances of Yij on the diagonal, then let Vi=Ai1∕2Ri(α)Ai1∕2∕ϕ indicate the working covariance matrix for these same measurements; Vi depends on the correlation structure Ri (α).
