Bioequivalence data arising from a two-period crossover trial are routinely analyzed to establish equivalence of the population means of a characteristic of the blood level curve, for example, AUC, for each formulation. Current methods only address equivalence of the formulation means, and recently, intrasubject variability, while intersubject variability is often neglected and assumed to be equal for each formulation. In this paper, the bioequivalence problem is cast into a linear structural relationship framework and a new two-step decision rule for assessing bioequivalence which takes intersubject variability into consideration is proposed. The two steps consist of 1) applying the current 90% parametric confidence interval method for equivalence of population means and 2) applying a 90% approximate confidence interval method for equivalence of population (intersubject) standard deviations. The ratio of the population standard deviations is shown to be the slope of the linear structural relationship. Bioequivalence is concluded if and only if both 1) and 2) result in an equivalence claim. An example is presented to illustrate the method.
CartwrightACInternational harmonization and consensus DIA meeting on bioavailability and bioequivalence testing requirements and standards. Drug Inf J. 1991;25:471–482.
2.
Code of Federal Regulations (1990). Title 21, Chapter 1: Food and Drugs, part 320 — Bioavailability and Bioequivalence Requirements, April 1, 1990, Sections 320.1–320.62. (abbreviated 21 CFR 320), Washington, D.C.: U.S. Government Printing Office.
3.
Commission of the European Communities.Investigation of bioavailability and bioequivalence. CPMP Working Party on Efficacy of Medicinal Products. Rules governing medicinal products in the European Community. 1991: Vol. III; 159–161.
4.
Nordic Council on Medicines.Bioavailability Studies in Man: Nordic Guidelines. NLN Publication No. 18. Uppsala, Sweden; 1987.
5.
Health Protection Branch, Department of Health and Welfare, Canada.Report A and B on bioavailability of oral formulations of drugs used for systemic efforts. Expert Advisory Committee on Bioavailability. Ottawa, Canada: Health Protection Branch; 1990.
6.
MetzlerCMBioavailability — a problem in equivalence. Biometrics. 1974:30;309–317.
7.
WestlakeWJBioequivalence testing — a need to rethink (Reader Reaction Response). Biometrics. 1981:37;591–593.
8.
AndersonSHauckWWA new procedure for testing equivalence in comparative bioavailability and other clinical trials. Comm Stat Theoret Meth. 1983:12;2663–2692.
9.
LockeCSAn exact confidence interval from untransformed data for the ratio of two formulation means. J Pharmacokinetics Biopharmaceutics. 1984:12;649–655.
10.
RoddaBEDavisRLDetermining the probability of an important difference in bioavailability. Clin Pharmacol Ther. 1980:28;247–252.
11.
MandallazDMauJComparison of different methods for decision-making in bioequivalence assessment. Biometrics. 1981:37;213–222.
12.
SteinijansVWDilettiEStatistical analysis of bioavailability studies: Parametric and nonparametric confidence intervals. European J Clin Pharmacol. 1983:24;127–136.
13.
SchuirmannDHA comparison of the two onesided tests procedure and the power approach for assessing the equivalence of average bioavailability. J Pharmacokinetics Biopharmaceutics. 1987:15;657–680.
14.
ChowSAlternative approaches for assessing bioequivalence regarding normality assumptions. Drug Inf J. 1980:24;753–762.
15.
HauschkeDSteinijansVWDilettiEA distribution-free procedure for the statistical analysis of bioequivalence studies. Inter J Clin Pharmacol, Therapy Toxicology. 1990:28;72–78.
16.
Report by the bioequivalence task force on recommendation from the bioequivalence hearing conducted by the FDA, September 29-October 1, 1986. Rockland, Maryland: U.S. Food and Drug Administration; 1988.
17.
Food and Drug Administration, Center for Drug Evaluation and Research, Office of Generic Drugs (1991). Proceedings of the Generic Drugs Advisory Committee held Sept. 26–27 in Bethesda, MD. C.A.S.E.T. Associates, Fairfax, Virginia.
18.
HwangSHuberPBHesneyMKwanKCBioequivalence and interchangeability (Open Forum). J Pharma Sciences. 1979:67; p. IV.
19.
HaynesJDStatistical simulation study of new proposed requirement for bioequivalency studies. J Pharma Sciences. 1981:70;673–675.
20.
MetzlerCMHuangDCStatistical methods for bioavailability and bioequivalence. Clin Res Pract Drug Regul Affairs. 1983:1;109–132.
21.
AlbertKSSmithRBBioavailability assessment as influenced by variation in drug absorption. In AlbertK.S. (ed.). Drug Absorption and Disposition: Statistical Considerations. Washington, D.C.: American Pharmaceutical Association, Academy of Pharmaceutical Sciences; 1980, 87.
22.
EkbohmGMelanderHThe subject-by-formulation interaction as a criterion of interchangeability of drugs. Biometrics. 1989:45;1249–1254.
23.
WestlakeWJ Bioavailability and bioequivalence of pharmaceutical formulations. In PeaceK. ed. Biopharmaceutical Statistics for Drug Development. New York: Marcel Dekker; 1988.
24.
AndersonSHauckWWConsideration of Individual Bioequivalence. J Pharmacokinetics Biopharmaceutics. 1990:18;259–273.
25.
BristolDRTesting equality of treatment variances in a two-by-two crossover study. J Biopharmaceutical Stat. 1991:1;185–192.
26.
LiuJPBioequivalence and intrasubject variability. J Biopharmaceutical Stat. 1991:1;205–219.
27.
FullerWAMeasurement Error Models. New York: John Wiley & Sons; 1987.
28.
BollenKAStructural Equations with Latent Variables. New York: John Wiley and Sons; 1989.
29.
KendallMGStuartA.The Advanced Theory of Statistics. Vol. 2, 4th ed.New York: Hafner; 1979.
30.
MetzlerCMStatistical criteria. In WellingP.TseF.L.S.DigheS.V. (eds.). Pharmaceutical Bioequivalence. New York: Marcel Dekker: 1991.
31.
SnikerisACBioequivalence as a linear structural relationship: estimation of formulation intersubject and intrasubject variability and a two-step method for assessing bioequivalence. Doctoral Dissertation, University of Delaware, May 1992.
