Skip to main content


Fig. 4 | BMC Medical Research Methodology

Fig. 4

From: Bayesian hierarchical piecewise regression models: a tool to detect trajectory divergence between groups in long-term observational studies

Fig. 4

Boxplots and mean “Age at divergence” (x) estimated across 100 simulations using the three methods. Bottom and top of the boxes are the lower (Q1) and upper quartiles (Q3), respectively; the bands near the middle of the boxes are the medians, the lengths of the boxes represent the interquartile range (IQR = Q3-Q1); the upper whiskers are defined as min(max(x), Q3 + 1.5 * IQR) and the lower whiskers as max(min(x), Q1 – 1.5 * IQR). Means of age at divergence across the 100 simulations for each scenario are indicated with empty circles. The horizontal dashed line indicates the true age at divergence set in the simulations (16.02 years old)

Back to article page