Skip to main content
Figure 4 | BMC Bioinformatics

Figure 4

From: Intensity dependent estimation of noise in microarrays improves detection of differentially expressed genes

Figure 4

The noise variance estimator has a χ2 distribution: Empirical probability density function (blue line) of the variance estimator and its fit (red dashed line) to the corresponding χ2 distribution (see (2)), in (a) and (c) the mean intensity is between 6 to 7, in (b) and (d) the mean intensity is between 10 to 11. In (a) and (b) we used 2 repeats and in (c) and (d) we used 8 repeats. Panels (e) and (f) show the dependence of the mean (panel (e)) and variance (panel (f)) of versus the number of repeats at hand, where the black and green lines represent different intensity bins, black for 6 <I < 7 and the green for 10 <I < 11. The dashed line in panel (f) is the variance expected from (3) (dataset used: GSE19921).

Back to article page