Estimation of accelerated hazards models based on case K informatively interval-censored failure time data

Area of Science:

• Biostatistics
• Survival Analysis
• Medical Statistics

Background:

• Accelerated hazards models are standard for failure time data with monotonic hazard functions.
• Existing methods for interval-censored data are limited and often assume independent censoring.
• Interval-censored data are prevalent in medical research, including clinical trials and follow-up studies.

Purpose of the Study:

• To develop a robust statistical inference method for interval-censored failure time data.
• To address limitations of existing methods, especially concerning informative censoring.
• To provide a flexible approach applicable to complex medical research scenarios.

Main Methods:

• Proposing a sieve borrow-strength method for statistical inference.
• Developing methods to handle case K interval-censored data.
• Establishing asymptotic properties for the proposed estimators.

Main Results:

• The proposed method effectively handles informative censoring in interval-censored data.
• Asymptotic properties of the estimators are theoretically established.
• Simulation studies confirm the good performance of the inference procedure.

Conclusions:

• The sieve borrow-strength method offers a powerful new tool for analyzing interval-censored failure time data.
• The method is suitable for medical research, including AIDS clinical trials.
• This approach advances statistical inference for complex survival data.