Skip to main content
Log in

Estimation After a Group Sequential Trial

  • Published:
Statistics in Biosciences Aims and scope Submit manuscript

Abstract

Group sequential trials are one important instance of studies for which the sample size is not fixed a priori but rather takes one of a finite set of pre-specified values, dependent on the observed data. Much work has been devoted to the inferential consequences of this design feature. Molenberghs et al. (Statistical Methods in Medical Research, 2012) and Milanzi et al. (Properties of estimators in exponential family settings with observation-based stopping rules, 2012) reviewed and extended the existing literature, focusing on a collection of seemingly disparate, but related, settings, namely completely random sample sizes, group sequential studies with deterministic and random stopping rules, incomplete data, and random cluster sizes. They showed that the ordinary sample average is a viable option for estimation following a group sequential trial, for a wide class of stopping rules and for random outcomes with a distribution in the exponential family. Their results are somewhat surprising in the sense that the sample average is not optimal, and further, there does not exist an optimal, or even, unbiased linear estimator. However, the sample average is asymptotically unbiased, both conditionally upon the observed sample size as well as marginalized over it. By exploiting ignorability they showed that the sample average is the conventional maximum likelihood estimator. They also showed that a conditional maximum likelihood estimator is finite sample unbiased, but is less efficient than the sample average and has the larger mean squared error. Asymptotically, the sample average and the conditional maximum likelihood estimator are equivalent. This previous work is restricted, however, to the situation in which the the random sample size can take only two values, \(N=n\) or \(N=2n\). In this paper, we consider the more practically useful setting of sample sizes in a the finite set \(\{n_1,n_2,\dots ,n_L\}\). It is shown that the sample average is then a justifiable estimator , in the sense that it follows from joint likelihood estimation, and it is consistent and asymptotically unbiased. We also show why simulations can give the false impression of bias in the sample average when considered conditional upon the sample size. The consequence is that no corrections need to be made to estimators following sequential trials. When small-sample bias is of concern, the conditional likelihood estimator (CLE) provides a relatively straightforward modification to the sample average. Finally, it is shown that classical likelihood-based standard errors and confidence intervals can be applied, obviating the need for technical corrections.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

References

  1. Armitage P (1975) Sequential medical trials. Blackwell, Oxford

    Google Scholar 

  2. Bassler D, Briel M, Montori VM, Lane M, Glasziou P, Zhou Q, Heels-Ansedell D, Walter SD, Guyatt GH (2010) Stopping randomized trials early for benefit and estimation of treatment effects. Systematic review and meta-regression analysis. J Am Med Assoc 303:1180–1187

    Article  Google Scholar 

  3. Blackwell D (1947) Conditional expectation and unbiased sequential estimation. Ann Math Stat 18:105–110

    Article  MathSciNet  MATH  Google Scholar 

  4. Casella G, Berger RL (2001) Statistical inference. Duxbury Press, Pacific Grove

    Google Scholar 

  5. Emerson SS (1988) Parameter estimation following group sequential hypothesis testing. PhD dissertation. University of Washington

  6. Emerson SS, Fleming TR (1990) Parameter estimation following group sequential hypothesis testing. Biometrika 77:875–892

    Article  MathSciNet  Google Scholar 

  7. Emerson SS, Gillen DL, Kittelson JK, Emerson SC, Levin GP (2012) RCTdesign: group sequential trial design. R package version 1

  8. Hughes MD, Pocock SJ (1988) Stopping rules and estimation problems in clinical trials. Stat Med 7:1231–1242

    Article  Google Scholar 

  9. Jennison C, Turnbull BW (2000) Group sequential methods with applications to clinical trials. Chapman & Hall/CRC, London

    MATH  Google Scholar 

  10. Kenward MG, Molenberghs G (1998) Likelihood based frequentist inference when data are missing at random. Stat Sci 13:236–247

    Article  MathSciNet  MATH  Google Scholar 

  11. Lehmann EL, Stein C (1950) Completeness in the sequential case. Ann Math Stat 21:376–385

    Article  MathSciNet  MATH  Google Scholar 

  12. Liu A, Hall WJ (1999) Unbiased estimation following a group sequential test. Biometrika 86:71–78

    Article  MathSciNet  MATH  Google Scholar 

  13. Liu A, Hall WJ, Yu KF, Wu C (2006) Estimation following a group sequential test for distributions in the one-parameter exponential family. Stat Sin 16:165–181

    MathSciNet  MATH  Google Scholar 

  14. Milanzi E, Molenberghs G, Alonso A, Kenward MG, Aerts M, Verbeke G, Tsiatis AA, Davidian M (2012) Properties of estimators in exponential family settings with observation-based stopping rules (under review)

  15. Molenberghs G, Kenward MG, Aerts M, Verbeke G, Tsiatis AA, Davidian M, Rizopoulos D (2014) On random sample size, ignorability, ancillarity, completeness, separability, and degeneracy: sequential trials, random sample sizes, and missing data. Stat Method Med Res 23:11–41

    Google Scholar 

  16. Rosner GL, Tsiatis AA (1988) Exact confidence intervals following a group sequential trial: a comparison of methods. Biometrika 75:723–729

    Article  MATH  Google Scholar 

  17. Siegmund D (1978) Estimation following sequential tests. Biometrika 64:191–199

    Google Scholar 

  18. Tsiatis AA, Rosner GL, Mehta CR (1984) Exact confidence intervals following a group sequential test. Biometrics 40:797–803

    Article  MathSciNet  MATH  Google Scholar 

  19. Todd S, Whitehead J, Facey KM (1996) Point and interval estimation following a sequential clinical trial. Biometrika 83:453–461

    Article  MATH  Google Scholar 

  20. Wald A (1945) Sequential tests of statistical hypotheses. Ann Math Stat 16:117–186

    Article  MathSciNet  MATH  Google Scholar 

  21. Whitehead J (1997) The design and analysis of sequential clinical trials, 2nd edn. Wiley, New York

    Google Scholar 

  22. Whitehead J (1999) A unified theory for sequential clinical trials. Stat Med 18:2271–2286

    Article  Google Scholar 

Download references

Acknowledgments

Elasma Milanzi, Geert Molenberghs, Michael G. Kenward, and Geert Verbeke gratefully acknowledge support from IAP research Network P7/06 of the Belgian Government (Belgian Science Policy). The work of Anastasios Tsiatis and Marie Davidian was supported in part by NIH grants P01 CA142538, R37 AI031789, R01 CA051962, and R01 CA085848.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Geert Molenberghs.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 107 KB)

Rights and permissions

Reprints and permissions

About this article

Cite this article

Milanzi, E., Molenberghs, G., Alonso, A. et al. Estimation After a Group Sequential Trial. Stat Biosci 7, 187–205 (2015). https://doi.org/10.1007/s12561-014-9112-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12561-014-9112-6

Keywords

Navigation