Skip to main content
Figure 4 | BMC Bioinformatics

Figure 4

From: Stronger findings from mass spectral data through multi-peak modeling

Figure 4

The use of data from multiple peaks and the peak shape information increased the accuracy at detecting significant covariate effects on simulated data. Accuracy of Models 1, 2 and 3 for simulated data is shown as a function of the sample-size in two settings: normal and high level of noise (left: σ2=1, and right: σ2=5, respectively). Top (a-b): Accuracy at inferring the significance of the generated covariate effects. Bottom (c-d): Normalized information distance (NID) between the inferred and the true clustering. An entirely random and an exactly correct clustering correspond to a NID of 1 and 0, respectively.

Back to article page