|
Abstract:
|
Since most biological systems are dynamic, time-course gene expression profiles may provide an important characterization of these systems. A number of statistical methods have been developed in recent years for identifying differentially expressed genes from time-course microarray experiments. However, proposed methods are sensitive in presence of outliers. In this paper, we propose a robust test method for identifying genes whose expression is different over time between two groups. We also propose a permutation-based multiple testing procedure based on the robust test statistic. Extensive simulations are conducted to investigate the performance of the permutation-based multiple testing procedure. Finally, the application of the proposed method is illustrated using the caenorhabditis elegans dauer developmental data.
|
