Skip to main content

Table 2 Comparison of bias(%) on parameter estimates by three methods: Bayesian, Gaussian quadrature and NLME-SAEM methods

From: Nonlinear mixed-effects HIV dynamic models with considering left-censored measurements

Case Method logc logδ logϕ d c 2 d δ 2 d ϕ 2 σ 2
A Bayesian 16.1 24.2 2.1 49.6 47.7 65.1 543
  Gaussian quadrature 15.6 24 2.2 53.1 44.3 75.5 512
  NLME-SAEM 15.2 23.7 2.4 47.3 46.4 69.5 484
B Bayesian 78 20 22 78 75 998 657
  Gaussian quadrature 72 25 16 94 61 932 586
  NLME-SAEM 71 22 19 90 68 970 490
  1. In case A, the below detection limit data are hold out before fitting each model; In case B, the below detection limit data are retained but assumed 25 as the true value. The number of simulation run is 100.