Skip to main content

Table 6 Fraction of false positives in smaller experiments.

From: Effects of filtering by Present call on analysis of microarray experiments

 

Unfiltered

All Absent

Fraction Present >0

# samples

0.050

0.010

0.0010

0.050

0.010

0.0010

0.050

0.010

0.0010

4

0.029

0.005

0.0005

0.035

0.007

0.0009

0.030

0.005

0.0004

6

0.036

0.006

0.0005

0.041

0.007

0.0007

0.033

0.005

0.0004

8

0.039

0.006

0.0050

0.044

0.008

0.0007

0.035

0.006

0.0004

  1. Permutations generating smaller experiments with 4, 6, or 8 samples per treatment group of the IFN MAS5 data such that no true positives would be expected were carried out 1000 times. Results shown are the average fraction called significant by the Welch's t-test for selected p-values (0.05, 0.01 and 0.001). Results are given for unfiltered data, probe sets called Absent for all samples, and data filtered using fraction Present >0.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us