Abstract:
Microarray experiments help scientists to study the expression level of thousands of
genes simultaneously. These experiments have many design challenges, such as, for example, which
mRNA samples should be co-hybridized together and which treatments should be labelled with
which fluorescent dye. Therefore a carefully designed microarray experiment to obtain efficient and
reliable data so as to ensure the precise estimate of comparisons of interest is required. The present
paper is concerned with A- and D-optimal row-column designs for two-colour microarray experiments,
with the array and dye effects treated as the column and row effects, respectively. Linear
mixed effects models were used to describe experiments for which a comparison of all possible pairs
of treatments is of particular interest by taking the arrays as random column effects. The results of
this study show that the optimal row-column designs under the linear fixed effects model are not
necessarily optimal under the linear mixed effects model setting.
