Investigating design for survival models

Abstract

The aim of this paper is to derive methodology for designing ‘time to event’ type experiments. In comparison to estimation, design aspects of ‘time to event’ experiments have received relatively little attention. We show that gains in efficiency of estimators of parameters and use of experimental material can be made using optimal design theory. The types of models considered include classical failure data and accelerated testing situations, and frailty models, each involving covariates which influence the outcome. The objective is to construct an optimal design based of the values of the covariates and associated model or indeed a candidate set of models. We consider D-optimality and create compound optimality criteria to derive optimal designs for multi-objective situations which, for example, focus on the number of failures as well as the estimation of parameters. The approach is motivated and demonstrated using common failure/survival models, for example, the Weibull distribution, product assessment and frailty models.

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

References

  1. Atkinson AC (2008) DT-optimum designs for model discrimination and parameter estimation. J Stat Plan Inference 138: 56–64

    MATH  Article  Google Scholar 

  2. Atkinson AC, Donev AN (1992) Optimum experimental designs, 1st edn. Oxford University Press Inc., Oxford

    Google Scholar 

  3. Blischke WR, Murthy DNP (2003) Case studies in reliability and maintenance. Wiley series in probability and statistics. Wiley, New York

    Google Scholar 

  4. Casella G, Berger RL (2002) Statistical inference. Duxbury Press, North Scituate, MA, USA

    Google Scholar 

  5. Chaloner K, Larntz K (1992) Bayesian design for accelerated life testing. J Stat Plan Inference 33: 245–259

    MATH  Article  Google Scholar 

  6. Clyde M, Chaloner K (1996) The equivalence of constrained and weighted designs in multiple objective design problems. J Am Stat Assoc 91: 1236–1244

    MATH  Article  MathSciNet  Google Scholar 

  7. Cook RD, Wong WK (1994) On the equivalence of constrained and compound optimal designs. J Am Stat Assoc 89: 687–692

    MATH  Article  MathSciNet  Google Scholar 

  8. Cramér H (1946) Mathematical methods of statistics. Princeton University Press, Princeton, pp 474–477

    Google Scholar 

  9. Crouchley R, Pickles AR (1995) Multivariate survival models for repeated and correlated events. J Stat Plan Inference 47: 95–110

    MATH  Article  Google Scholar 

  10. Danziger L (1970) Planning censored life tests for estimation of the hazard rate of a Weibull distribution with prescribed precision. Technometrics 12: 408–412

    Article  Google Scholar 

  11. D’Argenio DZ (1981) Optimal sampling times for pharmacokinetic experiments. J Pharmacokinet Biopharm 9: 739–756

    Article  Google Scholar 

  12. Duffull SB, Waterhouse TH, Eccleston JA (2005) Some considerations on the design of population pharmacokinetic studies. J Pharmacokinet Pharmacodyn 32: 441–457

    Article  Google Scholar 

  13. Erkanli A, Soyer R (2000) Simulation-based designs for accelerated life tests. J Stat Plan Inference 90: 335–348

    MATH  Article  MathSciNet  Google Scholar 

  14. Escobar LA, Meeker WQ Jr (1986) Elements of the Fisher information matrix for the smallest extreme value distribution and censored data. Appl Stat 35: 80–86

    MATH  Article  Google Scholar 

  15. Escobar LA, Meeker WQ Jr (1994) Fisher information matrix for the extreme value, normal and logistic distributions and censored data. Appl Stat 43: 533–540

    Article  Google Scholar 

  16. Escobar LA, Meeker WQ Jr (1995) Planning accelerated life tests with two or more experimental factors. Technometrics 37: 411–427

    MATH  Article  Google Scholar 

  17. Escobar LA, Meeker WQ Jr (1998) Fisher information matrices with censoring, truncation, and explanatory variables. Stat Sin 8: 221–237

    MATH  MathSciNet  Google Scholar 

  18. Gutierrez RG (2002) Parametric frailty and shared frailty survival models. Stata J 2: 22–44

    Google Scholar 

  19. Hougaard P (1995) Frailty models for survival data. Lifetime Data Anal 1: 255–273

    Article  Google Scholar 

  20. Huang YC, Wong WK (1998) Multiple-objective optimal designs. J Biopharm Stat 8: 635–643

    MATH  Article  Google Scholar 

  21. Hwang WT, Brookmeyer R (2003) Design of panel studies for disease progression with multiple stages. Lifetime Data Anal 9: 261–274

    MATH  Article  MathSciNet  Google Scholar 

  22. Klein JP, Moeschberger ML (2003) Survival analysis—techniques for censored and truncated data, 2nd edn. Springer, Berlin

    Google Scholar 

  23. McGilchrist CA, Aisbett CW (1991) Regression with frailty in survival analysis. Biometrics 47: 461–466

    Article  Google Scholar 

  24. McGree JM, Eccleston JA, Duffull SB (2008) Compound optimal design criteria for nonlinear models. J Biopharm Stat 18: 646–661

    Article  MathSciNet  Google Scholar 

  25. McGree JM, Eccleston JA (2008) Probability-based optimal design. Aust New Zealand J Stat 50: 13–28

    Article  MathSciNet  Google Scholar 

  26. Meeker WQ, Escobar LA (1998) Statistical methods for reliability data. Wiley series in probability and statistics. Wiley, New York

    Google Scholar 

  27. Meeker WQ, Escobar LA, Zayac SA (2003) Use of sensitivity analysis to assess the effect of model uncertainty in analyzing accelerated life test data. In: Blischke WR, Murthy DNP (eds) Case studies in reliability and maintenance. Wiley series in probability and statistics. Wiley, New York, pp. 135–162

    Google Scholar 

  28. Nelson W, Kielpinski T (1976) Theory for optimum censored accelerated life tests for normal and lognormal distributions. Technometrics 18: 105–114

    MATH  Article  Google Scholar 

  29. Nelson W, Meeker WQ (1978) Theory for optimum accelerated censored life tests for Weibull and Extreme value distributions. Technometrics 20: 171–177

    MATH  Article  Google Scholar 

  30. Onar A, Padgett WJ (2004) A penalized local D-optimality approach to design for accelerated test models. J Stat Plan Inference 119: 411–420

    MATH  Article  MathSciNet  Google Scholar 

  31. Shih JH, Louis TA (1995) Assessing gamma frailty models for clustered failure time data. Lifetime Data Anal 1: 205–220

    MATH  Article  MathSciNet  Google Scholar 

  32. Waterhouse TH (2005) Optimal experimental design for nonlinear and generalized linear models. Ph.D. thesis, University of Queensland

  33. Waterhouse TH, Eccleston JA, Duffull SB (2006) Optimal crossover designs for logistic regression models in pharmacodynamics. J Biopharm Stat 16: 881–894

    Article  MathSciNet  Google Scholar 

  34. Woods DC, Lewis SM, Eccleston JA, Russell KG (2006) Designs for generalized linear models with several variables and model uncertainty. Technometrics 48: 284–292

    Article  MathSciNet  Google Scholar 

  35. Zhang Y, Meeker WQ (2005) Bayesian life test planning for the Weibull distribution with given shape parameter. Metrika 61: 237–249

    MATH  Article  MathSciNet  Google Scholar 

  36. Zhang Y, Meeker WQ (2006) Bayesian methods for planning accelerated life tests. Technometrics 48: 49–60

    Article  MathSciNet  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to J. M. McGree.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

McGree, J.M., Eccleston, J.A. Investigating design for survival models. Metrika 72, 295–311 (2010). https://doi.org/10.1007/s00184-009-0254-3

Download citation

Keywords

  • Accelerated life tests
  • Compound criteria
  • Compromise design
  • D-optimality
  • Frailty models
  • P-optimality