gms | German Medical Science

63. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie e. V. (GMDS)

Deutsche Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie

02. - 06.09.2018, Osnabrück

The Schuirmann Constant: a new finding in the TOST-setting

Meeting Abstract

Suche in Medline nach

  • Christian Palmes - Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riß, Deutschland
  • Erich Bluhmki - Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach an der Riß, Deutschland; Hochschule Biberach, Biberach an der Riß, Deutschland

Deutsche Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie. 63. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie e.V. (GMDS). Osnabrück, 02.-06.09.2018. Düsseldorf: German Medical Science GMS Publishing House; 2018. DocAbstr. 160

doi: 10.3205/18gmds032, urn:nbn:de:0183-18gmds0325

Veröffentlicht: 27. August 2018

© 2018 Palmes et al.
Dieser Artikel ist ein Open-Access-Artikel und steht unter den Lizenzbedingungen der Creative Commons Attribution 4.0 License (Namensnennung). Lizenz-Angaben siehe http://creativecommons.org/licenses/by/4.0/.


Gliederung

Text

The two one-sided t-tests (TOST) is the equivalence test with many areas of application in the pharmaceutical industry, cf. FDA (2001) [1]. Proper sample size calculation is needed in order to show true equivalence with a certain power. Our starting motivation for this research was a better understanding of the limitations of the sample size approximation formulas in Bristol (1993) [2] and Shen (2015) [3]. For this, a novel power representation is derived that yields the correct asymptotics behind these formulas. Using our new power formula, we are even able to significantly improve the asymptotic properties of these formulas. As a further step, we address the problem of choosing a suitable mean-difference in TOST sample size calculations. To avoid the usual arbitrary point assumptions we suppose that the mean-difference follows an a-priori distribution. An exact closed-form power formula is presented for the uniform a-priori distribution together with a Monte Carlo simulation study. Ultimately, every a-priori distribution can be shown to correspond asymptotically to a point-wise mean-difference that we call its Schuirmann-constant S [4], which aims to support the investigator in finding a well-considered mean-difference for proper sample size calculations. Finally, we present a rule of thumb for choosing a suitable mean-difference motivated by our new asymptotic approach; practical implications will be discussed.

The authors declare that they have no competing interests.

The authors declare that an ethics committee vote is not required.


References

1.
FDA U.S. Department of Health and Human Services / Food and Drug Administration / Center for Drug Drug Evaluation and Research. Statistical Approaches to Establishing Bioequivalence. 2001.
2.
Bristol DR. Probabilities and sample sizes for the two one-sided tests procedure. Communications in Statistics - Theory and Methods. 1993;22(7):1953–61.
3.
Shen M, Cohen ER, Slud EV. Exact calculation of power and sample size in bioequivalence studies using two one-sided tests. Pharmaceut Statist. 2015;14:95–101.
4.
Schuirmann DJ. A comparison of the Two One-Sided Tests Procedure and the Power Approach for assessing the equivalence of average bioavailability. Journal of Pharmacokinetics and Biopharmaceutics. 1987;15(6):657–80.