Abstract
It is standard Bayesian practice that when more data become available, the posterior distribution is updated with new information and the posterior becomes the prior for the next posterior analysis. It is also standard Bayesian philosophy that an analysis be performed on the experiment that was actually run, and not on experiments that might have been run. Yet in experiments with informative interim stopping decisions, standard practice is not to condition the sampling density on interim decisions that are made. The consequence is that the likelihood is invariant to the decision. Information about the decision is not utilized. We examine the consequences of conditioning the sampling density on the interim decision for subsequent posterior analyses in the context of a two-stage design with an early stopping option.
Similar content being viewed by others
Change history
01 August 2023
A Correction to this paper has been published: https://doi.org/10.1007/s00362-023-01450-z
References
Berger JO (1985) Statistical decision theory and Bayesian analysis, 2nd edn. Springer, New York
Berger J, Wolpert R (1988) The likelihood principle (second edition). Institute of Mathematical Statistics. Lecture notes: Monographs Series, Institute of Mathematical Statistics. https://books.google.com/books?id=7fz8JGLmWbgC
Berry D, Ho C (1988) One-sided sequential stopping boundaries for clinical trials: a decision-theoretic approach. Biometrics 44(1):219–227. https://doi.org/10.2307/2531909
Birnbaum A (1962) On the foundations of statistical inference. J Am Stat Assoc 57(298):269–306
Box GE, Tiao GC (2011) Bayesian inference in statistical analysis. Wiley, Hoboken
Casella G, Berger R (2002) Statistical inference, 2nd edn. Duxberry advanced series. Cengage Learning, Boston
Cornfield J (1966) Sequential trials, sequential analysis and the likelihood principle. Am Stat 20(2):18–23
Efron B et al (1975) Defining the curvature of a statistical problem (with applications to second order efficiency). Ann Stat 3(6):1189–1242
Kalbfleisch JD (1975) Sufficiency and conditionality. Biometrika 62(2):251–259
Little RJ (2012) Calibrated Bayes, an alternative inferential paradigm for official statistics. J Off Stat 28(3):309
Liu A, Hall W (1999) Unbiased estimation following a group sequential test. Biometrika 86(1):71–78
Liu A, Hall W, Yu KF et al (2006) Estimation following a group sequential test for distributions in the one-parameter exponential family. Stat Sin 16(1):165–181
Marschner IC (2021) A general framework for the analysis of adaptive experiments. Stat Sci 36(3):465–492
Matsuo M (2021) Revisit to the likelihood principle. Ann Jpn Assoc Philos Sci 30:67–84
Mayo DG (2009) An error in the argument from conditionality and sufficiency to the likelihood principle. In Deborah G. Mayo & Aris Spanos (eds) Error and Inference: recent exchanges on experimental reasoning, reliability, and the objectivity and rationality of science Cambridge University Press pp. 305
Molenberghs G, Kenward MG, Aerts M et al (2014) On random sample size, ignorability, ancillarity, completeness, separability, and degeneracy: sequential trials, random sample sizes, and missing data. Stat Methods Med Res 23(1):11–41
Pocock SJ (1977) Group sequential methods in the design and analysis of clinical trials. Biometrika 64(2):191–199
Rosner GL, Laud PW, Johnson WO (2021) Bayesian thinking in biostatistics. CRC Press, Boca Raton
Tarima S, Flournoy N (2022a) The cost of sequential adaptation and the lower bound for mean squared error. arXiv:2209.02436
Tarima S, Flournoy N (2022b) Most powerful test sequences with early stopping options. Metrika 85(4):491–513
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The figure 1 caption is corrected. The bad breaks of the words and sentences are corrected.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Flournoy, N., Tarima, S. Posterior alternatives with informative early stopping. Stat Papers 64, 1329–1341 (2023). https://doi.org/10.1007/s00362-023-01429-w
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00362-023-01429-w