Application of multilevel models in the evaluation of bioequivalence (Ⅱ) / 中华流行病学杂志

The main purpose of this paper is to explore the applicability of multivariate multilevel models for bioequivalence evaluation. Using an example of a 4×4 cross-over test design in evaluating bioequivalence of homemade and imported rosiglitazone maleate tablets,this paper illustrated the multivariate-model-based method for partitioning total variances of In (AUC) and In (C_(max)) in the framework of multilevel models. It examined the feasibility of multivariate multilevel models in directly evaluating average bioequivalence (ABE),population bioequivalence (PBE) and individual bioequivalenc (IBE). Taking into account the correlation between In (AUC) and In (C_(max)) of rosiglitazone maleate tablets,the proposed models suggested no statistical difference between the two effect measures in their ABE bioequivalence via joint tests,whilst a contradictive conclusion was derived based on univariate multilevel models. Furthermore,the PBE and IBE for both In (AUG) and In(C_(max)) of the two types of tablets were assessed with no statistical difference based on estimates of variance components from the proposed models. Multivariate multilevel models could be used to analyze bioequivalence of multiple effect measures simultaneously and they provided a new way of statistical analysis to evaluate bioequivalence.

Applying multilevel models in evaluation of bioequivalence (I) / 中华流行病学杂志

This study aims to explore the application value of multilevel models for bioequivalence evaluation. Using a real example of 2 x 4 cross-over experimental design in evaluating bioequivalence of antihypertensive drug, this paper explores complex variance components corresponding to criteria statistics in existing methods recommended by FDA but obtained in multilevel models analysis. Results are compared with those from FDA standard Method of Moments, specifically on the feasibility and applicability of multilevel models in directly assessing the bioequivalence (ABE), the population bioequivalence (PBE) and the individual bioequivalence (IBE). When measuring ln (AUC), results from all variance components of the test and reference groups such as total variance (sigma(TT)(2) and sigma(TR)(2)), between-subject variance (sigma(BT)(2) and sigma(BR)(2)) and within-subject variance (sigma(WT)(2) and sigma(WR)(2)) estimated by simple 2-level models are very close to those that using the FDA Method of Moments. In practice, bioequivalence evaluation can be carried out directly by multilevel models, or by FDA criteria, based on variance components estimated from multilevel models. Both approaches produce consistent results. Multilevel models can be used to evaluate bioequivalence in cross-over test design. Compared to FDA methods, this one is more flexible in decomposing total variance into sub components in order to evaluate the ABE, PBE and IBE. Multilevel model provides a new way into the practice of bioequivalence evaluation.