Using densities of estimators to compare pharmacokinetic experiments☆
Received 4 October 2000; accepted 23 October 2000.
Abstract
Different designs of experiments are compared according to the shape, concentration, etc. of the densities of the least-squares estimator (conditional densities, marginal densities). In contrast with D'Argenio (J. Pharmacokinetics Biopharmaceutics 9(16) (1981) 739–756), where marginal densities have been obtained by simulations, we present here a faster procedure based on well-elaborated approximations of the densities. The stress is on the graphical presentation of the results.
aLaboratoire I3S, CNRS/Université de Nice-Sophia Antipolis, Les Algorithmes/Bâtiment Euclide B, 2000 route des Lucioles, BP 121, 06903 Sophia-Antipolis Cedex, France
bDepartment of Probability and Statistics, Comenius University, Mlynská dolina, 84215 Bratislava, Slovakia
Corresponding author
☆ This work was partly supported by a project from the Slovak Grant Agency.
ABSTRACT