Impact of model misspecification at design (and/or) estimation step in population pharmacokinetic studies

Autor:	Azzedine Aouimer, Yann Merlé, Michel Tod
Rok vydání:	2004
Předmět:	Pharmacology Statistics and Probability Estimation Hyperparameter education.field_of_study Models Statistical Computer science Population Context (language use) Statistics Econometrics Humans Pharmacology (medical) Pharmacokinetics education
Zdroj:	Journal of biopharmaceutical statistics. 14(1)
ISSN:	1054-3406
Popis:	The aim of this work is to quantitatively assess the impact of structural model misspecifications on the estimates of mean and interindividual variability of clearance in the context of population approaches. This assessment is conducted from simulated datasets. Our results show that impact magnitude of model misspecification on the estimates depends on the step at which it occurs (design optimization and/or estimation), on the hyperparameter of interest, and on the estimation method. Bias and precision might be affected differently as well as powers of model discrimination tests. Some practical guidelines for reducing impact of model misspecifications are also suggested.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87e8cc91d2ebbc3ddb6b1eda2f2d8dc3 https://pubmed.ncbi.nlm.nih.gov/15027510 Zobrazit plný text záznamu Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.