Skip to main content

Table 1 Error on FDR estimation in the case of two replicates and 500 increased genes (p <= 0.1)

From: Rank Difference Analysis of Microarrays (RDAM), a novel approach to statistical analysis of microarray expression profiling data

FDR #1 #2 #3 #4 #5 #6 #7 #8 #9 #10
5% 1 (12) 2 (8) 0 (3) 0 (3) 0 0 (0) 0 (0) 0 (0) 0 (0) 0 (2)
10% 2 (73) 3 (25) 0 (14) -2 (37) -1 (2) 2 (20) 0 (0) 1 (12) -1 (20) -2 (20)
15% 1 (160) 0 (84) -3 (68) -4 (59) -3 (5) 2 (58) -4 (41) -3 (40) -4 (63) -4 (57)
20% 2 (217) -6 (157) -11 (130) -9 (129) -5 (65) 0 (134) -8 (152) -6 (81) -11 (146) -10 (136)
  1. Comparisons were made between two groups of two replicates. The first group is composed of synthetic data sets made from the experimental replicates Wt-t0a and Wt-t0b, in which 1000 genes (500 increased and 500 decreased) are changed (p <= 0.10), and the second group is composed of synthetic data sets without extra variation. Ten comparisons with different combinations of data sets were made. For each set of selected genes we computed the difference between the real number of false positives and the estimated number of false positives. In the first column the FDR estimation is indicated; other columns give the number of increased genes either faultly assigned as true positive (positive difference) or as false positive (negative difference) in each of the ten comparisons (numbered from #1 to #10). In parentheses is indicated the number of genes selected for the given value of the FDR estimator.