Skip to main content

Advertisement

Table 2 Posterior mean parameter estimates for Bayesian hierarchical Piecewise BMI trajectory for best fitting trajectory divergence models in males and females (Models E)

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

   Females
Model E
Males
Model E
β0 I 26.5 (0.20) 27.46 (0.16)
β1 S1 0.67 (0.012) 0.61 (0.01)
β2 S2 −0.49 (0.015) −0.46 (0.06)
CP CP 16.02 (0.29) 21.62 (0.42)
CP T2DM CP 12.37 (1.21) 6.47 (1.23)
σβ0   2.07 (0.05) 2.36 (0.07)
σβ1   0.02 (0.005) 0.06 (0.004)
σβ2   0.07 (0.006) 0.05 (0.004)
σ β1β2   0.11 (0.05) 0.14 (0.03)
σ CP   3.1 (0.26) 4.3 (0.2)
σ   1.33 (0.02) 1.21 (0.01)
β log(insulin)   1.01 (0.04) 0.98 (0.03)
  1. Posterior standard deviations (uncertainty in the parameters) are reported in brackets. Reported β0 coefficients are in kg/m2, β1 and β2 are in kg/m2 per year, CP and CP T2DM are in years. All σ coefficients are standard deviations for the corresponding growth parameters and the residual error. β log(insulin) coefficients are in kg/m2 for a 1 sd increase in log(insulin) level