Random-Effects Linear Modeling and Sample Size Computations for Two Special Crossover Designs of Average Bioequivalence Studies

• Activity Number: 31
• Type: Contributed
• Date/Time: Sunday, August 3, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Francisco J. Diaz*+ and Michel Berg and Ron Krebill and Timothy Welty and Barry E. Gidal and Rita Alloway and Michael Privitera
• Companies: University of Kansas Medical Center and University of Rochester Medical Center and University of Kansas Medical Center and Drake University and University of Wisconsin and University of Cincinnati and University of Cincinnati Neuroscience Institute
• Keywords: Power analysis ; Cross-over studies ; Bioequivalence studies ; Random-effects linear models ; EQUIGEN studies ; Personalized medicine

Abstract

Due to concern in the epilepsy medical community and to the interest of the United States Food and Drug Administration (FDA) in revising approaches to the approval of generic drugs, the FDA is currently supporting ongoing bioequivalence studies of antiepileptic drugs, the EQUIGEN studies. During the design of these crossover studies, the researchers could not find commercial or non-commercial statistical software that quickly allowed computing sample sizes for their designs, particularly software implementing FDA requirement of using random effects linear models (RELMs) for the analyses of bioequivalence studies. Thus, SAS programs and tables were developed to achieve this goal. We present these published tables, which evaluate sample sizes of average bioequivalence studies based on the two cross-over designs used in the EQUIGEN studies: the 4-period, 2-sequence, 2-formulation design, and the 6-period, 3-sequence, 3-formulation design. We also provide a presentation of the statistical modeling of data from bioequivalence studies that highlights the important mathematical role of RELMs in theoretical formulations in personalized medicine, with special emphasis on power analyses.