Abstract
The aim of this paper is to develop a Bayesian local influence method (Zhu et al. 2009, submitted) for assessing minor perturbations to the prior, the sampling distribution, and individual observations in survival analysis. We introduce a perturbation model to characterize simultaneous (or individual) perturbations to the data, the prior distribution, and the sampling distribution. We construct a Bayesian perturbation manifold to the perturbation model and calculate its associated geometric quantities including the metric tensor to characterize the intrinsic structure of the perturbation model (or perturbation scheme). We develop local influence measures based on several objective functions to quantify the degree of various perturbations to statistical models. We carry out several simulation studies and analyze two real data sets to illustrate our Bayesian local influence method in detecting influential observations, and for characterizing the sensitivity to the prior distribution and hazard function.
Similar content being viewed by others
References
Amari S (1990) Differential-geometrical methods in statistics, 2nd edn. Lecture notes in statistics, no. 28. Springer-Verlag, Berlin
Anderson PK, Borgan O, Gill RD, Keiding N (1993) Statistical models based on counting processes. Springer-Verlag, New York
Arjas E, Gasbarra D (1994) Nonparametric Bayesian inference from right censored survival data using the Gibbs sampler. Stat Sin 4: 505–524
Berger JO (1990) Robust Bayesian analysis: sensitivity to the prior. J Stat Plan Inference 25: 303–328
Berger JO (1994) An overview of robust Bayesian analysis. TEST 3: 5–58
Berger JO, Rios Insua D, Ruggeri F (2000) Bayesian robustness. In: Rios Insua D, Ruggeri F (eds) Robust Bayesian analysis. Springer-Verlag, New York
Brown ER, Ibrahim JG (2003) A Bayesian semiparametric joint hierarchical model for longitudinal and survival data. Biometrics 59: 221–228
Brown ER, Ibrahim JG (2003) Bayesian approaches to joint cure rate and longitudinal models with applications to cancer vaccine trials. Biometrics 59: 686–693
Brown ER, Ibrahim JG, DeGruttola V (2005) A flexible B-spline model for multiple longitudinal biomarkers and survival. Biometrics 61: 64–73
Carlin BP, Polson NG (1991) An expected utility approach to influence diagnostics. J Am Stat Assoc 86: 1013–1021
Chen Z, Dunson DB (2004) Bayesian estimation of survival functions under stochastic precedence. Lifetime Data Anal 10: 159–173
Chen M-H, Ibrahim JG, Sinha D (1999) A new Bayesian model for survival data with a surviving fraction. J Am Stat Assoc 94: 909–919
Chen M-H, Shao Q-M, Ibrahim JG (2000) Monte Carlo methods in Bayesian computation. Springer-Verlag, New York
Chen MH, Harrington DP, Ibrahim JG (2002a) Bayesian cure rate models for malignant melanoma: a case study of eastern cooperative oncology group trial E1690. Appl Stat 51: 135–150
Chen MH, Ibrahim JG, Lipsitz SR (2002b) Bayesian methods for missing covariates in cure rate models. Lifetime Data Anal 8: 117–146
Chen MH, Ibrahim JG, Sinha D (2002c) Bayesian inference for multivariate survival data with a surviving fraction. J Multivar Anal 80: 101–126
Chen MH, Ibrahim JG, Sinha D (2004) A new joint model for longitudinal and survival data with a cure fraction. J Multivar Anal 91: 18–34
Chen MH, Ibrahim JG, Shao QM (2006) Posterior propriety and computation for the Cox regression model with applications to missing covariates. Biometrika 93: 791–807
Chi Y, Ibrahim JG (2006) Joint models for multivariate longitudinal and multivariate survival data. Biometrics 62: 432–445
Chi Y, Ibrahim JG (2007) A new class of joint models for longitudinal and survival data accomodating zero and non-zero cure fractions: a case study of an international breast cancer study group trial. Stat Sin 17: 445–462
Cho H, Ibrahim JG, Sinha D, Zhu H (2009) Bayesian case influence diagnostics for survival models. Biometrics 65: 116–124
Christensen R (1997) Log-linear models and logistic regression. Springer-Verlag, Inc, New York
Cook RD (1986) Assessment of local influence (with discussion). J R Stat Soc B 48: 133–169
Cooner F, Banerjee S, Carlin BP, Sinha D (2007) Flexible cure rate modelling under latent activation schemes. J Am Stat Assoc 102: 560–572
Cox DR (1972) Regression models and life tables (with discussion). J R Stat Soc B 34: 187–220
Cox DR, Reid N (1987) Parameter orthogonality and approximate conditional influence (with discussion). J R Stat Soc B 49: 1–39
De Iorio M, Johnson WO, Müller P, Rosner GL (2009) Bayesian nonparametric nonproportional hazards survival modeling. Biometrics 65: 762–771
Dunson DB, Dinse GE (2002) Bayesian models for multivariate current status data with informative censoring. Biometrika 58: 79–88
Dunson DB, Herring AH (2003) Bayesian inferences in the Cox model for order restricted alternatives. Biometrics 59: 918–925
Dunson DB, Herring AH (2005) Bayesian model selection and averaging in additive and proportional hazards. Lifetime Data Anal 11: 213–232
Dunson DB, Park H-H (2008) Kernel stick breaking processes. Biometrika 95: 307–323
Dykstra RL, Laud PW (1981) A Bayesian nonparametric approach to reliability. Ann Stat 9: 356–367
Fleming TR, Harrington DP (1991) Counting processes and survival analysis. Wiley, New York
Gallant AR, Nychka DW (1987) Semiparametric maximum likelihood estimation. Economatrica 55: 363–390
Geisser S (1993) Predictive inference: an introduction. Chapman & Hall, London
Gelfand AE, Dey DK (1994) Bayesian model choice: asymptotics and exact calculations. J R Stat Soc B 56: 501–514
Gelfand AE, Dey DK, Chang H (1992) Model determination using predictive distributions, with implementation via sampling-based methods (Disc: P160-167). In: Bernardo JM, Berger JO, Dawid AP, Smith AFM (eds) Bayesian statistics, vol 4. Oxford University Press, Oxford, pp 147–159
Gustafson P (1996a) Local sensitivity of inferences to prior marginals. J Am Stat Assoc 91: 774–781
Gustafson P (1996) Local sensitivity of posterior expectations. Ann Stat 24: 174–195
Gustafson P (2000) Local robustness in Bayesian analysis. In: Rios Insua D, Ruggeri F (eds) Robust Bayesian analysis. Springer-Verlag, New York, pp 71–88
Gustafson P, Wasserman L (1995) Local sensitivity diagnostics for Bayesian inference. Ann Stat 23: 2153–2167
Hanson T, Johnson WO (2002) Modeling regression error with a mixture of Polya trees. J Am Stat Assoc 97: 1020–1033
Hanson T, Johnson W, Laud P (2009) Semiparametric inference for survival models with step process covariates. Can J Stat 37: 60–79
Ibrahim JG, Chen M-H, Sinha D (2001) Bayesian survival analysis. Springer-Verlag, Inc, New York
Ibrahim JG, Chen M-H, Sinha D (2004) Bayesian methods for joint modeling of longitudinal and survival data with applications to cancer vaccine studies. Stat Sin 14: 863–883
Ibrahim JG, Chen MH, Kim S (2008) Bayesian variable selection for the Cox regression model with missing covariates. Lifetime Data Anal 14: 496–520
Johnson W, Geisser S (1983) A predictive view of the detection and characterization of influential observations in regression analysis. J Am Stat Assoc 78: 137–144
Johnson W, Geisser S (1985) Estimative influence measures for the multivariate general linear model. J Stat Plan Inference 11: 33–56
Kalbfleisch JD (1978) Nonparametric Bayesian analysis of survival time data. J R Stat Soc B 40: 214–221
Kalbfleisch JD, Prentice RL (2002) The statistical analysis of failure time data, 2nd edn. Wiley, New York
Kass RE, Tierney L, Kadane JB (1989) Approximate methods for assessing influence and sensitivity in Bayesian analysis. Biometrika 76: 663–674
Kim S, Xi Y, Chen M-H (2009) A new latent cure marker model for survival data. Ann Appl Stat 3: 1124–1146
Lawless JF (2003) Statistical models and methods for life time data, 2nd edn. Wiley, New York
Leonard T (1978) Density estimation, stochastic processes and prior information. J R Stat Soc B 40: 113–146
McCulloch RE (1989) Local model influence. J Am Stat Assoc 84: 473–478
Moreno E (2000) Global Bayesian robustness for some classes of prior distributions. In: Rios Insua D, Ruggeri F (eds) Robust Bayesian analysis. Springer-Verlag, New York
Oakley J, O’Hagan A (2004) Probabilistic sensitivity analysis of complex models: a Bayesian approach. J R Stat Soc B 66: 751–769
Peng F, Dey DK (1995) Bayesian analysis of outlier problems using divergences measures. Can J Stat 23: 199–213
Pennell ML, Dunson DB (2006) Bayesian semiparametric dynamic frailty models for multiple event time data. Biometrics 62: 1044–1052
Pettit LI (1986) Diagnostics in Bayesian model choice. Statistician 35: 183–190
Rodriguez A, Dunson DB, Gelfand AE (2008) The nested Dirichlet process (with discussion). J Am Stat Assoc 103: 1131–1144
Sinha D (1993) Semiparametric Bayesian analysis of multiple event time data. J Am Stat Assoc 88: 979–983
Sinha D, Dey DK (1997) Semiparametric Bayesian analysis of survival data. J Am Stat Assoc 92: 1195–1212
Sinha D, Maiti T (2004) A Bayesian approach for the analysis of panel-count data with dependent termination. Biometrics 60: 34–40
Sinha D, Ibrahim JG, Chen M-H (2003) A Bayesian justification of Cox’s partial likelihood. Biometrika 90: 629–641
Sinha D, Maiti T, Ibrahim JG, Ouyang B (2008) Current methods for recurrent events data with dependent termination: a Bayesian perspective. J Am Stat Assoc 103: 866–878
Sinha D, McHenry BM, Lipsitz SR, Ghosh M (2009) Empirical Bayes estimation for additive hazards regression models. Biometrika 96: 529–544
Sivaganesan S (2000) Global and local robustness approaches: uses and limitations. In: Rios Insua D, Ruggeri F (eds) Robust Bayesian analysis. Springer-Verlag, New York, pp 89–108
Vaupel JM, Manton KG, Stallard E (1979) The impact of heterogeneity in individual frailty on the dynamics of mortality. Demography 16: 439–454
Weiss R (1996) An approach to Bayesian sensitivity analysis. J R Stat Soc B 58: 739–750
Weiss RE, Cho M (1998) Bayesian marginal influence assessment. J Stat Plan Inference 71: 163–177
Weiss RE, Cook RD (1992) A graphical case statistic for assessing posterior influence. Biometrika 79: 51–55
Yakovlev AY (1994) Letter to the editor. Stat Med 13: 983–986
Yin G, Ibrahim JG (2005a) A class of Bayesian shared gamma frailty models with multivariate failure time data. Biometrics 61: 208–216
Yin G, Ibrahim JG (2005b) Bayesian frailty models based on Box-Cox transformed hazards. Stat Sin 15: 781–794
Yin G, Ibrahim JG (2005c) A general class of Bayesian survival models with zero and non-zero cure fractions. Biometrics 61: 403–412
Yin G, Ibrahim JG (2005d) Cure rate models: a unified approach. Can J Stat 33: 559–570
Zhu HT, Lee SY (2001) Local influence for incomplete data models. J R Stat Soc B 63: 111–126
Zhu HT, Zhang HP (2004) A diagnostic procedure based on local influence. Biometrika 91: 579–589
Zhu HT, Ibrahim JG, Lee SY, Zhang HP (2007) Perturbation selection and influence measures in local influence analysis. Ann Stat 35: 2565–2588
Zhu HT, Ibrahim JG, Tang NS (2009) Bayesian influence analysis: a geometric approach. Submitted
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ibrahim, J.G., Zhu, H. & Tang, N. Bayesian local influence for survival models. Lifetime Data Anal 17, 43–70 (2011). https://doi.org/10.1007/s10985-010-9170-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10985-010-9170-0