Assume that there is no correlation in the FIM between the fixed and random effects, and set these elements inĤ = Reduced FIM and computing all derivatives with respect to the standard deviation of the residual unexplained variation (sqrt(SIGMA) in NONMEM). No assumption that fixed and random effects are uncorrelated.ġ = Reduced FIM. Should the algorithm output results intermittently. This optimization is always added to the end of the sequential optimization.Ĭontains control arguments specified for each method separately. c("ARS") isįor Adaptive Random Search optim_ARS. Should the discrete design variables be optimized?Īre the number of sample times per group being optimized?Īre the number of individuals per group being optimized?Ī vector of optimization methods to use in a sequentialįashion. Should the continuous design variables be optimized? Loop_methods = ifelse ( length ( method ) > 1, TRUE, FALSE ), Use_laplace = poped.db $ settings $ iEDCalculationType, Ofv_calc_type = poped.db $ settings $ ofv_calc_type,Īpprox_type = poped.db $ settings $ iApproximationMethod,ĭ_switch = poped.db $ settings $ d_switch,ĮD_samp_size = poped.db $ settings $ ED_samp_size, Opt_inds = poped.db $ settings $ optsw ,įim.calc.type = poped.db $ settings $ iFIMCalculationType, Opt_samps = poped.db $ settings $ optsw , (compared to the start of the series) is less than stop_crit_eff. Iterations, or until the efficiency of the design after the current series Then the series of optimization methods will be run for iter_max Specified then the methods are run in series. The function works for both discrete andĬontinuous optimization variables.
0 kommentar(er)
