Skip to main content

Table 1 The true values and mean estimates of population dynamic parameters with 100 replications as well as the corresponding bias, RMSE

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

   logc logδ logϕ d c 2 d δ 2 d ϕ 2 σ 2
Case A         
  True value 1.1 -1 3 0.25 0.04 0.0625 0.01
  Mean estimate 0.9 -0.8 3.07 0.13 0.06 0.11 0.05
  Bias(%) 15.2 23.7 2.4 47.3 46.4 69.5 484
  RMSE(%) 78 69 4.6 85 198 147 658
Case B         
  True value 1.1 -1 3 0.25 0.04 0.0625 0.01
  Mean estimate 1.9 -0.8 3.6 0.03 0.067 0.669 0.06
  Bias(%) 71 22 19 90 68 970 490
  RMSE(%) 141 58 23 105 125 1013 687
Case C         
  True value 1.1 -1 3 0.25 0.04 0.0625 0.01
  Mean estimate 1.2 -1.0 3.02 0.12 0.036 0.048 0.02
  Bias(%) 9.9 0.2 0.9 53 9.5 23.3 83
  RMSE(%) 54 5 3 75 39 211 783
  1. In case A, the below detection limit data are hold out before fitting the model; In case B, the below detection limit data are retained but assumed 25 as the true value; In case C, the below detection limit data are considered as censored data and censoring mechanism is introduced by the proposed method.