Skip to main content
Fig. 7 | BMC Medical Research Methodology

Fig. 7

From: Combined models for pre- and post-treatment longitudinal biomarker data: an application to CD4 counts in HIV-patients

Fig. 7

Kernel density plots (a–c) for the ‘true’ baseline square root CD4 counts and (d–f) histograms of the last observed square-root CD4 count before treatment. a–c Kernel density plots for the ‘true’ baseline square root CD4 counts for each individual (u i ), approximating the posterior distribution of each as normal (with subject-specific standard deviation as estimated during model fitting), and d–f histograms of the last observed square-root CD4 count before treatment for those individuals in whom this was recorded within 6 months of treatment initiation (n=170, n=141 and n=486, respectively). Graphs in the top row a, d relate to patients initiating treatment within 6 months of seroconversion, those in the centre row b, e relate to patients initiating treatment beyond 6 months but within 1 year and those on the lower row c, f are for patients who started treatment beyond 1 year

Back to article page