Mixed Effects Models in Drug Stability
Tuesday 3 June, 10:20--12:10

Organizer: Jim COLAIANNE
Merck Sharp \& Dohme
Moderator: Jim COLAIANNE
Merck Sharp \& Dohme

Use of Random Slopes Model in Drug Stability

John MURPHY
Eli Lilly, Indianapolis, IN, USA
Methods for determining shelf life, expiry limit, and release limits are developed and compared. The FDA/ICH method is compared to random slopes methods based on ANOVA Estimators and to Maximum Likelihood Estimators from SAS Proc Mixed. The performance of the methods is compared on the basis of the bias and precision of the estimates generated.

[John Murphy, Eli Lilly, Drop Code 2233, Lilly Corporate Ctr, Indianapolis, IN 46285-0002]


A Comparison of Fixed Effects Models and Mixed Models for the Calculation of Shelf Life

Arthur R SILVERBERG
Trilogy Consulting Corporation, Princeton, NJ, USA
For pharmaceutical products, a stability study is normally conducted to calculate a shelf life (expiratory dating period). A comparison of several methods for computing the expiration dating period (shelf life) is explored using real datasets. All methods are based upon a regression procedure. The method for the traditional NDA three batch sample is to consider batches as fixed and take the batch with the shortest expiration dating period. When marketing batches become available there may be many more than three batches and this fixed effects methodology may not give reasonable answers. Fixed effects methods include calculating using fixed effects regression models with and without common error, and common slope. Random coefficients models were also fit with slopes and intercepts independent and with an unstructured covariance matrix. Prediction limits, confidence limits and tolerance limits were calculated with these random effects models and compared to the fixed effects models.

[Arthur R. Silverberg, Trilogy Consulting Corporation, USA.]


Back to JRC program
Back to JRC Home Page