Advertisement

Conditional Inference in Two-Stage Adaptive Experiments via the Bootstrap

  • Adam LaneEmail author
  • HaiYing Wang
  • Nancy Flournoy
Conference paper
Part of the Contributions to Statistics book series (CONTRIB.STAT.)

Abstract

We study two-stage adaptive designs in which data accumulated in the first stage are used to select the design for a second stage. Inference following such experiments is often conducted by ignoring the adaptive procedure and treating the design as fixed. Alternative inference procedures approximate the variance of the parameter estimates by approximating the inverse of expected Fisher information. Both of these inferential methods often rely on normal distribution assumptions in order to create confidence intervals. In an effort to improve inference, we develop bootstrap methods that condition on a non-ancillary statistic that defines the second stage design.

References

  1. 1.
    Baldi Antognini, A., Giovagnoli, A.: On the asympotic inference for response-adaptive experiments. METRON – Int. J. Stat. 49, 29–46 (2006)MathSciNetGoogle Scholar
  2. 2.
    Dette, H., Bornkamp, B., Bretz, F.: On the efficiency of two-stage response-adaptive designs. Stat. Med. 32, 1646–1660 (2013)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Efron, B.: Nonparametric standard errors and confidence intervals. Can. J. Stat. 9, 139–158 (1981)CrossRefzbMATHMathSciNetGoogle Scholar
  4. 4.
    Efron, B., Hinkley, D.V.: Assessing the accuracy of the maximum likelihood estimate: observed versus expected Fisher information. Biometrika 65, 457–483 (1978)CrossRefzbMATHMathSciNetGoogle Scholar
  5. 5.
    Lane, A., Yao, P., Flournoy, N.: Information in a two-stage adaptive optimal design. J. Stat. Plan. Inference 144, 173–187 (2014)CrossRefzbMATHMathSciNetGoogle Scholar
  6. 6.
    Pronzato, L., Pazman, A.: Design of Experiments in Nonlinear Models. Springer, New York (2013)CrossRefzbMATHGoogle Scholar
  7. 7.
    Rosenberger, W.F., Hu, F.: Bootstrap methods for adaptive designs. Stat. Med. 18, 1757–1767 (1999)CrossRefGoogle Scholar
  8. 8.
    Whitehead, J.: On the bias of maximum likelihood estimation following a sequential test. Biometrika 73, 573–581 (1986)CrossRefzbMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Cincinnati Children’s Hospital Medical CenterCincinnatiUSA
  2. 2.University of New HampshireDurhamUSA
  3. 3.University of MissouriColumbiaUSA

Personalised recommendations