A Note on Comparing Two Binomial Proportions in Confirmatory Noninferiority Trials

Abstract

We evaluate the performance of two commonly used methods to construct confidence intervals for noninferiority decisions when the primary end point is binary. The two methods are the classical asymptotic normal approximation procedure and the same procedure with the Hauck-Anderson type of continuity correction. Simulations were conducted to explore the rate of erroneously concluding noninferiority when the new treatment is worse than the active control by the amount defined by the noninferiority margin. The evaluation was conducted with sample sizes relevant to the confirmatory trials. Based on the findings from the simulations, we provide some practical guidance to individuals responsible for the analysis of such trial data.

Keywords

Asymptotic normal approximation Confidence intervals Continuity correction Simulations Type I error rate

Get full access to this article

View all access options for this article.

References

StatXact 4 [computer program). Cambridge, MA: Cytel Software Corporation; 1995.

Newcombe

Interval estimation for the difference between independent proportions: Comparison of 11 methods. Stat Med. 1998;17: 873–890.

Fleiss

Statistical Methods for Rates and Proportions. New York, NY: Wiley; 1981.

Chan

ISF

Exact tests of equivalence and efficacy with a non-zero lower bound for comparative studies. Stat Med. 1998;17:1403–1413.

Chan

ISF

Providing non-inferiority or equivalence of two treatments with dichotomous end-points using exact methods. Stat Methods Med Res. 2003;12:37–58.

Kang

Chen

An approximate unconditional test of non-inferiority between two proportions. Stat Med. 2000;19:2089–2100.

Chen

A quasi-exact method for the confidence intervals of the difference of two independent binomial proportions in small sample cases. Stat Med. 2002;21:943–956.

Bristol

Clinical equivalence. J Biopharm Stat. 1999;9:549–561.

Chuang-Stein

Clinical equivalence—a clarification. Drug Inf J. 1999;33:1189–1194.

10.

Rodary

Com-Nougue

Tournade

How to establish equivalence between treatments: A one-sided clinical trial in paediatric oncology. Stat Med. 1989;8:593–598.

11.

Farrington

Manning

Test statistics and sample size formulae for comparative binomial trials with null hypothesis of non-zero risk difference or non-unity relative risk. Stat Med. 1990;9:1447–1454.

12.

Dunnet

Gent

Significance testing to establish equivalence between treatments with special reference to data in the form of 2 times 2 tables. Biometrics. 1977;33:593–602.

13.

Miettinen

Nurminen

Comparative analysis of two rates. Stat Med. 1985;4:213–226.

14.

Hauck

Anderson

A comparison of large sample confidence interval methods for the differences of two binomial probabilities. Am Stat. 1986;40:318–322.

15.

A comparative study of some statistical procedures in establishing therapeutic equivalence of nonsystemic drugs with binary endpoints. Drug Inf J. 1997;31:1291–1300.

16.

Agresti

Categorical Data Analysis. New York, NY: Wiley; 2002.

17.

Elashoff

nQuery Advisor. 1995.

18.

S-plus 6 [computer program]. Seattle, WA: Insightful Corporation; 2001.