The performance of linear mixed effects models for the comparison of dissol
ution profiles is examined. This type of model is frequently used by statis
ticians, but is rather unknown to people that work in dissolution laborator
ies. Hence, an extensive theoretical part was introduced to make the method
ology more accessible. Firstly, repeated measures ANOVA is discussed, follo
wed by the 'real' linear mixed effects models. The theory is applied to two
types of dissolution data: one corresponding to an immediate and another t
o a slow release formulation. We tried to use as much as possible the stand
ard settings of the statistical software (S-plus). Suggestions are given to
solve problems encountered during model fitting. It was found that the sta
tistical limits are much more discriminative than the similarity factor. (C
) 2001 Elsevier Science B.V. All rights reserved.