Bayesian and Frequentist Approaches for a Tractable Parametric General Class of Hazard-Based Regression Models: An Application to Oncology Data

In this study, we consider a general, flexible, parametric hazard-based regression model for censored lifetime data with covariates and term it the “general hazard (GH)” model. Some well-known models, such as accelerated failure time (AFT), proportional (PH) well (AH) accounting crossed survival curves, are sub-classes of general proposed class covariate’s effect is identified having two distinct components, namely relative ratio time-scale change on progression. The new approach more adaptive to modelling could give accurate forecasts. nested structure that includes AFT, AH, PH models in may offer numerical tool identifying which them most appropriate certain dataset. propose method applying these various based tractable distribution baseline hazard, known generalized log-logistic (GLL) distribution. This closed under all PH, AFT frameworks can incorporate basic rate shapes interest practice, decreasing, constant, increasing, V-shaped, unimodal, J-shaped rates. Bayesian frequentist approaches were used estimate parameters. Comprehensive simulation studies evaluate performance model’s estimators its structure. A right-censored cancer dataset illustrate application approach. performs both real datasets, demonstrating importance developing flexible time-independent time-dependent evaluating function over time.