Résumé
Microarray experiments allow RNA level measurements for many genes in multiple samples. However, mining the biological information from the large sets of data generated by microarrays requires the use of appropriate statistical methods to adjust the observed values for experimentally introduced variability (normalization process) before testing differences among samples. Normalization of microarray experiments is a critical step for reducing false positives and false negatives. This paper explores the normalization of cDNA microarray experiments by a method that uses the blank spot intensity values to make spatial adjustment (SA) of both foreground and background DNA spot intensity values, by fitting an autoregressive mixed linear model through the residual maximum likelihood (REML) methodology in the direction of the rows and the columns of the microarray. Application of this spatial normalization to three cDNA array experiments serves as a case study to validate the SA. Results show that the spatial analysis allows selection of candidate genes with lesser numbers of false positive and false negative genes.