Information matrices for mixed effects models with applications to the optimality of repeated measurements designs (Q1205463)

The paper considers a repeated measurements (RM) design with carry over effects. A general mixed effects model is considered for a response vector and information matrices for the parameters involved in the model are developed. An identity, necessary to hold in the construction of information matrices, is also proved. Use of information matrices has been made to show the optimality of uniform balanced RM designs. The proofs involve quite lengthy but important expressions in matrices.