Premium
PI‐76
Author(s) -
Zhou J.,
Li J.,
Allred R.,
Ling J.,
Mount J.,
Toh M.,
Pithavala Y.,
Amantea M.,
Raber S.
Publication year - 2006
Publication title -
clinical pharmacology and therapeutics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.941
H-Index - 188
eISSN - 1532-6535
pISSN - 0009-9236
DOI - 10.1016/j.clpt.2005.12.097
Subject(s) - bioavailability , crossover study , pharmacology , crossover , order (exchange) , medicine , computer science , chemistry , business , artificial intelligence , alternative medicine , finance , pathology , placebo
BACKGROUND Cost‐efficient trial designs have drawn considerable attention ( Pharmaceutical Statistics; 2005; 4:152‐160 ). Dropouts often occur in clinical trials. This study is to investigate the effect of dropouts on the cost efficiency of five commonly used, statistically optimal or near‐optimal higher‐order crossover designs for comparative bioavailability studies. METHODS Probabilistic models were used to simulate three dropout patterns (decreasing, constant, and increasing) after generation of multivariate normal data under wide scenarios of variability and correlations (CV = 10% to 40%; ρ = 0.2 to 0.8). Monte Carlo simulations and mixed‐effects models were carried out to obtain empirical sample sizes of the five designs using Schuirmann's TOST Procedure, under an 80% power and a 5% significance level, based on the equivalence criteria (80%, 125%). The five designs, cost function and calculation were previously described (Abstract PII‐150, ASCPT 2005). RESULTS D3×2 is generally the best with dropouts. But D4×4, often the best design without dropouts, becomes the second worst with dropouts. D4×2 is the best when the screening cost is high and period cost does not vary. D2×4 is still the worst. CONCLUSIONS The 3‐period 2‐sequence design is recommended with consideration of dropouts, unless screening costs are high, in which case the 4‐period 2‐sequence design becomes preferable. The 2‐period 4‐sequence and the 4‐period 4‐sequence designs are least favorable in terms of cost efficiency. Clinical Pharmacology & Therapeutics (2005) 79 , P27–P27; doi: 10.1016/j.clpt.2005.12.097