Abstract
We present sample size determination using exact approaches for testing the ratio of incidence rates from a two-arm non-inferiority trial. The first approach is the exact conditional approach by treating the total number of events from two groups fixed, and the other is the exact unconditional approach based on maximization. Exact approaches guarantee the type I error rate which is often not satisfied in the commonly used asymptotic approaches on the basis of the corresponding limiting distributions of test statistics. We provide tables for sample size determination in commonly used cases in practice, and an example is used to show the application of these exact approaches. Sample size comparison using different exact approaches concludes that the exact unconditional approach based on the Wald-type test statistic has good performance in balanced studies.
Similar content being viewed by others
References
Brown CC, Green SB (1982) Additional power computations for designing comparative Poisson trials. Am J Epidemiol 115(5):752–758
Buehler RJ (1957) Confidence intervals for the product of two binomial parameters. J Am Stat Assoc 52(280):482–493
Casella G, Berger RL (2002) Statistical inference, 2nd edn. Thomson Learning, Belmont
Chapman DG (1952) On tests and estimates for the ratio of Poisson means. Ann Inst Stat Math 4(1):45–49
Chiu SN, Wang L (2009) Homogeneity tests for several Poisson populations. Comput Stat Data Anal 53(12):4266–4278
Graham PL, Mengersen K, Morton AP (2003) Confidence limits for the ratio of two rates based on likelihood scores: non-iterative method. Stat Med 22(12):2071–2083
Gu K, Ng HKT, Tang ML, Schucany WR (2008) Testing the ratio of two Poisson rates. Biom J 50(2):283–298
Han C (2008) Comparing two independent incidence rates using conditional and unconditional exact tests. Pharm Stat 7(3):195–201
Huffman MD (1984) An improved approximate two-sample Poisson test. J R Stat Soc Ser C Appl Stat 33(2):224–226
Krishnamoorthy K, Thomson J (2004) A more powerful test for comparing two Poisson means. J Stat Plan Inference 119(1):23–35
Li H-Q, Tang M-L, Wong W-K (2014) Confidence intervals for ratio of two Poisson rates using the method of variance estimates recovery. Comput Stat 29:869–889
Liu MT, Hsueh H-M (2013) Exact tests of the superiority under the Poisson distribution. Stat Probab Lett 83(5):1339–1345
Lui K-J (2005) Sample size calculation for testing non-inferiority and equivalence under Poisson distribution. Stat Methodol 2(1):37–48
Rothman KJ, Lash TL, Greenland S (2012) Modern epidemiology, mid-cycle revision edition, third edn. Lippincott Williams & Wilkins, Philadelphia
Shan G (2014a) Exact approaches for testing non-inferiority or superiority of two incidence rates. Stat Probab Lett 85:129–134
Shan G (2014b) Exact one-sided confidence limit for the ratio of two Poisson rates (under review)
Shan G (2015) Exact statistical inference for categorical data. Academic Press, New York
Shan G, Ma C (2016) Unconditional tests for comparing two ordered multinomials. Stat Methods Med Res 25(1):241–254
Shan G, Ma C, Hutson AD, Wilding GE (2012) An efficient and exact approach for detecting trends with binary endpoints. Stat Med 31(2):155–164
Shan G, Moonie S, Shen J (2014) Sample size calculation based on efficient unconditional tests for clinical trials with historical controls. J Biopharm Stat . doi:10.1080/10543406.2014.1000545
Shan G, Wang W (2013) ExactCIdiff: an R package for computing exact confidence intervals for the difference of two proportions. R J 5(2):62–71
Shan G, Wilding GE, Hutson AD, Gerstenberger S (2016) Optimal adaptive two-stage designs for early phase II clinical trials. Stat Med 35(8):1257–1266
Stucke K, Kieser M (2013) Sample size calculations for noninferiority trials with Poisson distributed count data. Biom J 55(2):203–216
Suissa S, Shuster JJ (1985) Exact unconditional sample sizes for the 2 \(\times \) 2 binomial trial. J R Stat Soc Ser A (General) 148(4):317–327
Wang W, Shan G (2015) Exact confidence intervals for the relative risk and the odds ratio. Biometrics 71(4):985–995
Acknowledgments
We would like to thank the Editor, the Associate Editor and two referees for their valuable comments and suggestions that helped to improve this manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Shan, G. Exact sample size determination for the ratio of two incidence rates under the Poisson distribution. Comput Stat 31, 1633–1644 (2016). https://doi.org/10.1007/s00180-016-0654-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-016-0654-6