Lifetime Data Analysis

, Volume 14, Issue 3, pp 316–332 | Cite as

A new class of survival regression models with heavy-tailed errors: robustness and diagnostics

  • Michelli Barros
  • Gilberto A. Paula
  • Víctor Leiva


Birnbaum-Saunders models have largely been applied in material fatigue studies and reliability analyses to relate the total time until failure with some type of cumulative damage. In many problems related to the medical field, such as chronic cardiac diseases and different types of cancer, a cumulative damage caused by several risk factors might cause some degradation that leads to a fatigue process. In these cases, BS models can be suitable for describing the propagation lifetime. However, since the cumulative damage is assumed to be normally distributed in the BS distribution, the parameter estimates from this model can be sensitive to outlying observations. In order to attenuate this influence, we present in this paper BS models, in which a Student-t distribution is assumed to explain the cumulative damage. In particular, we show that the maximum likelihood estimates of the Student-t log-BS models attribute smaller weights to outlying observations, which produce robust parameter estimates. Also, some inferential results are presented. In addition, based on local influence and deviance component and martingale-type residuals, a diagnostics analysis is derived. Finally, a motivating example from the medical field is analyzed using log-BS regression models. Since the parameter estimates appear to be very sensitive to outlying and influential observations, the Student-t log-BS regression model should attenuate such influences. The model checking methodologies developed in this paper are used to compare the fitted models.


Generalized Birnbaum-Saunders distribution Likelihood methods Local influence Log-linear models Residual analysis Robustness Sinh-normal distribution 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Balakrishnan N, Leiva V, López J (2007) Acceptance sampling plans from truncated life tests from generalized Birnbaum-Saunders distribution. Commun Stat Simul Comput 36: 643–656CrossRefzbMATHGoogle Scholar
  2. Berkane M, Kano Y, Bentler PM (1994) Pseudo maximum likelihood estimation in elliptical theory: effects of misspecification. Comput Stat Data Anal 18: 255–267CrossRefMathSciNetGoogle Scholar
  3. Birnbaum ZW, Saunders SC (1969) A new family of life distributions. J Appl Prob 6: 319–327CrossRefMathSciNetzbMATHGoogle Scholar
  4. Collett D (2003) Modelling survival data in medical research. Chapman and Hall, LondonGoogle Scholar
  5. Cook RD (1986) Assessment of local influence. J Roy Stat Soc B 48: 133–169zbMATHGoogle Scholar
  6. Cramér H (1999) Mathematical methods of statistics. Princeton University Press, PrincetonzbMATHGoogle Scholar
  7. Davison AC, Gigli A (1989) Deviance residuals and normal scores plots. Biometrika 76: 211–221CrossRefzbMATHGoogle Scholar
  8. Desmond A (1985) Stochastic models of failure in random environments. Can J Stat 13: 171–183CrossRefMathSciNetzbMATHGoogle Scholar
  9. Díaz-García JA, Leiva V (2005) A new family of life distributions based on elliptically contoured distributions. J Stat Plan Infer 128:445–457 (Erratum: J Stat Plan Infer 137:1512–1513)Google Scholar
  10. Dupuis DJ, Mills JE (1998) Robust estimation of the Birnbaum-Saunders distribution. IEEE Trans Rel 47: 88–95CrossRefGoogle Scholar
  11. Escobar LA, Meeker WQ (1992) Assessing influence in regression analysis with censored data. Biometrics 48: 507–528CrossRefMathSciNetzbMATHGoogle Scholar
  12. Fang KT, Kotz S, Ng KW (1990) Symmetric multivariate and related distribution. Chapman and Hall, LondonGoogle Scholar
  13. Fernandez C, Steel M (1999) Multivariate Student-t regression models: pitfalls and inference. Biometrika 86: 153–167CrossRefMathSciNetzbMATHGoogle Scholar
  14. Galea M, Leiva V, Paula GA (2004) Influence diagnostics in log-Birnbaum-Saunders regression models. J Appl Stat 31: 1049–1064CrossRefMathSciNetzbMATHGoogle Scholar
  15. Johnson NL, Kotz S, Balakrishnan N (1995) Continuous univariate distributions, vol 2. Wiley, New YorkzbMATHGoogle Scholar
  16. Kalbfleisch JD, Prentice RL (2002) The statistical analysis of failure time data. Wiley, New YorkzbMATHGoogle Scholar
  17. Klein JP, Moeschberger ML (1997) Survival analysis: techniques for censored and truncated data. Springer, New YorkzbMATHGoogle Scholar
  18. Lange KL, Little JA, Taylor MG (1989) Robust statistical modelling using the t distribution. J Amer Stat Soc 84: 881–896MathSciNetGoogle Scholar
  19. Lawless JF (2002) Statistical models and methods for lifetime data, 2nd edn. Wiley, New YorkGoogle Scholar
  20. Lee ET, Wang JW (2003) Statistical methods for survival data analysis. Wiley, New YorkzbMATHGoogle Scholar
  21. Leiva V, Barros M, Paula GA, Galea M (2007) Influence diagnostics in log-Birnbaum-Saunders regression models with censored data. Comput Stat Data Anal 51: 5694–5707CrossRefGoogle Scholar
  22. Leiva V, Barros M, Paula GA, Sanhueza A (2008a) Generalized Birnbaum-Saunders distribution applied to air pollutant concentration. Environmetrics 19 (in press) (doi: 10.1002/env.861)
  23. Leiva V, Riquelme M, Balakrishnan N, Sanhueza A (2008b) Lifetime analysis based on the generalized Birnbaum-Saunders distribution. Comput Stat Data Anal 52: 2079–2097CrossRefGoogle Scholar
  24. Leiva V, Sanhueza A, Angulo JM (2008c) A length-biased version of the Birnbaum-Saunders distribution with application in water quality. Stoch Environ Res Risk Assess (in press) (doi: 10.1007/s00477-008-0215-9)
  25. Lesaffre E, Verbeke G (1998) Local influence in linear mixed models. Biometrics 54: 570–582CrossRefzbMATHGoogle Scholar
  26. Meeker WQ, Escobar LA (1998) Statistical methods for reliability data. Wiley, New YorkzbMATHGoogle Scholar
  27. Ortega EMM, Bolfarine H, Paula GA (2003) Influence diagnostic in generalized log-gamma regression models. Comput Stat Data Anal 40: 165–186CrossRefMathSciNetGoogle Scholar
  28. Owen WJ, Padgett WJ (1999) Accelerated test models for system strength based on Birnbaum-Saunders distribution. Lifetime Data Anal 5: 133–147CrossRefMathSciNetzbMATHGoogle Scholar
  29. Owen WJ, Padgett WJ (2000) A Birnbaum-Saunders accelerated life model. IEEE Trans Rel 49: 224–229CrossRefGoogle Scholar
  30. Poon WY, Poon YS (1999) Conformal normal curvature and assessment of local influence. J Roy Stat Soc B 61: 51–61CrossRefMathSciNetzbMATHGoogle Scholar
  31. Rieck JR, Nedelman JR (1991) A log-linear model for the Birnbaum-Saunders distribution. Technometrics 33: 51–60CrossRefzbMATHGoogle Scholar
  32. Sanhueza A, Leiva V, Balakrishnan N (2008) The generalized Birnbaum-Saunders distribution and its theory, methodology and application. Commun Stat Theor Meth 37: 645–670CrossRefzbMATHGoogle Scholar
  33. Saunders SC (1974) A family of random variables closed under reciprocation. J Amer Stat Soc 6: 319–327MathSciNetGoogle Scholar
  34. Taylor J, Verbyla A (2004) Joint modeling of location and scale parameters of t distribution. Stat Model 4: 91–112CrossRefMathSciNetzbMATHGoogle Scholar
  35. Therneau TM, Grambsch PM, Fleming TR (1990) Martingale-based residuals for survival models. Biometrika 77: 147–160CrossRefMathSciNetzbMATHGoogle Scholar
  36. Tsionas EG (2001) Bayesian inference in Birnbaum-Saunders regression. Commun Stat Theor Meth 30: 179–193CrossRefMathSciNetzbMATHGoogle Scholar
  37. Verbeke G, Molenberghs G (2000) Linear mixed models for longitudinal data. Springer, New YorkzbMATHGoogle Scholar
  38. Xie FC, Wei BC (2007) Diagnostics analysis for log-Birnbaum-Saunders regression models. Comput Stat Data Anal 51: 4692–4706CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Michelli Barros
    • 1
  • Gilberto A. Paula
    • 2
  • Víctor Leiva
    • 3
  1. 1.Department of Mathematics and StatisticsUniversidade Federal de Campina GrandeCampina GrandeBrazil
  2. 2.Department of StatisticsUniversidade de São PauloSão PauloBrazil
  3. 3.Department of StatisticsUniversidad de ValparaísoValparaísoChile

Personalised recommendations