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.

Text 124978.pdf - Published Version Restricted to Repository staff only Download (292kB) Official URL or Download Paper: https://science.lpnu.ua/mmc/all-volumes-and-issues...

Actions (login required)

View Item