Comparison of Dissolution Profiles: A Statistician's Perspective
| Autor: | Thomas Hoffelder |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Multivariate analysis
Models Statistical Operations research Computer science Chemistry Pharmaceutical Public Health Environmental and Occupational Health Inference Context (language use) 030226 pharmacology & pharmacy 01 natural sciences Test (assessment) 010104 statistics & probability 03 medical and health sciences Variable (computer science) 0302 clinical medicine Solubility Sample size determination Sample Size Multivariate Analysis Pharmacology (medical) 0101 mathematics Pharmacology Toxicology and Pharmaceutics (miscellaneous) Equivalence (measure theory) Software Statistician |
| Zdroj: | Therapeutic innovationregulatory science. 52(4) |
| ISSN: | 2168-4804 |
| Popis: | Dissolution profile comparisons are used in the context of postapproval changes where the manufacturer has to demonstrate that the quality of the product is not affected by the change. Around this topic, basic statistical principles are in conflict with widely used interpretations of current guidelines, resulting in time-intensive discussions in pharmaceutical practice. From a statistician's perspective, the following suggestions could improve the situation regarding statistical analysis, inference, and interpretation: (1) A clear definition of the variability criterion for the similarity factor, such as that found in the EMA guideline, would be helpful. (2) Sample size recommendations should be interpreted as minimum, not as maximum, requirements. (3) In case of several batches per reference or test group, pooled comparisons should be performed instead of multiple batch-to-batch comparisons. (4) FDA Guideline recommendations concerning multivariate equivalence procedures for highly variable dissolution profiles are based on the state of statistical knowledge in 1997 and need to be updated. (5) The T2 test for equivalence is an appropriate method for comparing highly variable dissolution profiles. Application of the T2 test for equivalence enables reliable equivalence decisions and satisfies the intention of reaching scientific evidence in decision making. Software implementations of this test are available in R and SAS. The article is a summary of the poster of the same name presented at the DIA FDA Statistics Forum 2016. The poster took the third place in the poster award of the conference. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink