Regression analysis of doubly censored failure time data using the additive hazards model

Area of Science:

• Biostatistics
• Survival Analysis
• Epidemiology

Background:

• Doubly censored failure time data present unique analytical challenges.
• Existing regression methods primarily rely on the proportional hazards model, which may not always be suitable.
• There is a need for alternative regression models for doubly censored data.

Purpose of the Study:

• To investigate regression analysis of doubly censored data using the additive hazards model.
• To propose an estimating equation approach for inference on regression parameters.
• To provide a flexible and easily implementable method for analyzing complex survival data.

Main Methods:

• Utilized the additive hazards model for regression analysis.
• Developed an estimating equation approach for parameter inference.
• Established the statistical properties of the proposed regression parameter estimates.

Main Results:

• The proposed method provides a viable alternative to proportional hazards models for doubly censored data.
• The statistical properties of the regression parameter estimates are theoretically established.
• The method was successfully applied to real-world data from an AIDS cohort study.

Conclusions:

• The additive hazards model offers a valuable framework for regression analysis of doubly censored failure time data.
• The proposed estimating equation approach is practical and statistically sound.
• This method enhances the analysis of survival data in epidemiological and clinical research.