Skip to main content
Figure 1 | BMC Bioinformatics

Figure 1

From: Inferring signalling networks from longitudinal data using sampling based approaches in the R-package 'ddepn'

Figure 1

Laplace prior curve. Unnormalised prior densities, depending on difference Δ ij . Left: γ is constant, for increasing λ a 'flattening' of the prior curve can be observed. For small λ, small differences to the reference retrieve higher weight than large differences. For large λ, all differences are weighted approximately equal. Right: λ is fixed, when γ increases, a plateau at the upper bound can be seen. This means that small differences to the reference are not penalised as strong as for small γ, leaving the control that up to some deviance from the reference a high prior weight is retained.

Back to article page