Skip to main content
Fig. 3 | BMC Bioinformatics

Fig. 3

From: Practical identifiability in the frame of nonlinear mixed effects models: the example of the in vitro erythropoiesis

Fig. 3

Model (2) is unidentifiable. A Likelihood distribution over 50 SAEM runs on the Model (2). B Cumulated AIC weights over the 50 runs of SAEM. The 45 runs associated to the lowest likelihood values (i.e. those that add up to 95% of the total weight of the 50 runs) are coloured in red. C Normalized parameter values in the 45 convergents runs of SAEM. Displayed are the distributions of estimated parameter values, normalized by their median. D Distribution of the \(\eta\)-shrinkage values for the individual parameters in the 45 convergent runs of SAEM

Back to article page