  Research articleFiltering for increased power for microarray data analysisAmber J Hackstadt Center for Bioinformatics and Department of Statistics, Colorado State University, Fort Collins, CO, 80523, USA
BMC Bioinformatics 2009, 10:11doi:10.1186/1471-2105-10-11
Additional filesAdditional file 1: Detailed Statistics on Power from Simulation Study. The table displays the 5th, 25th, 50th, 75th, and 95th quantiles of the observed power for simulation runs. Power was calculated with and without variance filtering for both FDR methods(Benjamini-Hochberg and q-value) using a stated FDR level of 0.05. Both dependent and independent cases were considered over a range of π0 values, where π0 is the proportion of genes which are truly not differentially expressed. Format: XLS Size: 23KB Download file This file can be viewed with: Microsoft Excel Viewer Additional file 2: Detailed Statistics on FDR from Simulation Study. The table displays the 5th, 25th, 50th, 75th, and 95th quantiles of observed FDR for simulation runs. Observed FDR was calculated with and without variance filtering for both FDR methods (Benjamini-Hochberg and q-value) using a stated FDR level of 0.05. Both dependent and independent cases were considered over a range of π0 values, where π0 is the proportion of genes which are truly not differentially expressed. Format: XLS Size: 23KB Download file This file can be viewed with: Microsoft Excel Viewer |
|
|
|
 |  | Log on / register Feedback | Support | My details |
on Google Scholar
author email
corresponding author email|
|
| © 1999-2010 BioMed Central Ltd unless otherwise stated. Part of Springer Science+Business Media. |