Imputation Methods for a Bathtub Hazard Model with Right-Censored and Interval-Censored Data

In this study, we extended a two-parameter bathtub hazard model that exhibits either an increasing or a bathtub-shaped failure rate depending on its shape parameter.  The model was expanded to include covariates in the presence of right- and interval-censored data.  To handle interval-censored data, we employed two imputation techniques: midpoint and random imputation.  A simulation study was conducted to evaluate and compare the performance of these imputation methods using standard error (SE) and root mean square error (RMSE) values.  The findings indicated that random imputation outperforms midpoint imputation in most instances, achieving lower SE and RMSE across different censoring proportions and sample sizes.  To demonstrate the practical applicability of the extended model, a real dataset on the occurrence of oral lesions in children after liver transplantation was used for illustrative purposes.

bathtub-shaped
right-censored
interval-censored
imputation
midpoint
random
  1. Lai C. D., Xie M., Murthy D. N. P. B.  Ch. 3. Bathtub-shaped failure rate life distributions.  Handbook of Statistics.  20, 69–104 (2001).
  2. Rajarshi S., Rajarshi M. B.  Bathtub distributions: a review.  Communications in Statistics – Theory and Methods.  17 (8), 2597–2621 (1988).
  3. Thach T. T., Briš R.  An additive Chen-Weibull distribution and its applications in reliability modeling.  Quality and Reliability Engineering International.  37 (1), 352–373 (2021).
  4. Mudholkar G. S., Srivastava D. K.  Exponentiated Weibull Family for Analyzing Bathtub Failure-Rate Data.  IEEE Transactions on Reliability.  42 (2), 299–302 (1993).
  5. Bebbington M., Lai C.-D., Zitikis R.  A flexible Weibull extension.  Reliability Engineering & System Safety.  92 (6), 719–726 (2007).
  6. Liao Q., Ahmad Z., Mahmoudi E., Hamedani G. G.  A New Flexible Bathtub-Shaped Modification of the Weibull Model: Properties and Applications.  Mathematical Problems in Engineering.  2020, 3206257 (2020).
  7. Chen Z.  A new two-parameter lifetime distribution with bathtub shape or increasing failure rate function.  Statistics & Probability Letters.  49 (2), 155–161 (2000).
  8. Wu J.-W., Lu H.-L., Chen C.-H., Wu C.-H.  Statistical inference about the shape parameter of the new two-parameter bathtub-shaped lifetime distribution.  Quality and Reliability Engineering International.  20 (6), 607–616 (2004).
  9. Wu S.-J.  Estimation of the two-parameter bathtub-shaped lifetime distribution with progressive censoring.  Journal of Applied Statistics.  35 (10), 1139–1150 (2008).
  10. Rastogi M. K., Tripathi Y. M., Wu S.-J.  Estimating the parameters of a bathtub-shaped distribution under progressive type-II censoring.  Journal of Applied Statistics.  39 (11), 2389–2411 (2012).
  11. Wang R., Sha N., Gu B., Xu X.  Statistical Analysis of a Weibull Extension with Bathtub-Shaped Failure Rate Function.  Advances in Statistics.  2014, 304724 (2014).
  12. Xie M., Tang Y., Goh T. N.  A modified Weibull extension with bathtub-shaped failure rate function.  Reliability Engineering & System Safety.  76 (3), 279–285 (2002).
  13. Tang Y., Xie M., Goh T. N.  Statistical Analysis of a Weibull Extension Model.  Communications in Statistics – Theory and Methods.  32 (5), 913–928 (2003).
  14. Chaubey Y. P., Zhang R.  An extension of Chen's family of survival distributions with bathtub shape or increasing hazard rate function.  Communications in Statistics – Theory and Methods.  44 (19), 4049–4064 (2015).
  15. Bhatti F. A., Hamedani G. G., Najibi S. M., Ahmad M.  On the Extended Chen Distribution: Development, Properties, Characterizations and Applications.  Annals of Data Science.  8 (1), 159–180 (2021).
  16. Tarvirdizade B., Ahmadpour M.  A New Extension of Chen Distribution with Applications to Lifetime Data.  Communications in Mathematics and Statistics.  9 (1), 23–38 (2021).
  17. Sarhan A. M., Mustafa A.  A new extension of the two-parameter bathtub hazard shaped distribution.  Scientific African.  17, e01345 (2022).
  18. Lui K.-J., Darrow W. W., Rutherford G. W.  A model-based estimate of the mean incubation period for AIDS in homosexual men.  Science.  240 (4857), 1333–1335 (1988).
  19. Mariotto A. B., Mariotti S., Pezzotti P., Rezza G., Verdecchia A.  Estimation of the acquired immunodeficiency syndrome incubation period in intravenous drug users: A comparison with male homosexuals.  American Journal of Epidemiology.  135 (4), 428–437 (1992).
  20. Williams C. F., Klinzman D., Yamashita T. E., Xiang J., Polgreen P. M., Rinaldo C., Liu C., Phair J., Margolick J. B., Zdunek D., Hess G., Stapleton J. T.  Persistent GB Virus C Infection and Survival in HIV-Infected Men.  The New England Journal of Medicine.  350 (10), 981–990 (2004).
  21. Law C. G., Brookmeyer R.  Effects of mid-point imputation on the analysis of doubly censored data.  Statistics in Medicine.  11 (12), 1569–1578 (1992).
  22. Zyoud A. M. H., Elfaki F. A. M., Hrairi M.  Parametric model based on imputation techniques for partly interval censored data.  Journal of Physics: Conference Series.  949, 012002 (2017).
  23. Kim H. J., Kim S., Lee E.  Cox proportional hazards regression for interval-censored data with an application to college entrance and parental job loss.  Economies.  10 (9), 218 (2022).
  24. Arasan J., Midi H.  Bootstrap based diagnostics for survival regression model with interval and right-censored data.  Austrian Journal of Statistics.  52 (2), 66–85 (2023).
  25. Calsavara V. F., Rodrigues A. S., Rocha R., Tomazella V., Louzada F.  Defective regression models for cure rate modeling with interval-censored data.  Biometrical Journal.  61 (4), 841–859 (2019).