Sample size determination in complex clinical trials comparing more than two groups for survival endpoints

Area of Science:

• Biostatistics
• Clinical Trial Design
• Survival Analysis

Background:

• Accurate sample size calculation is crucial for the validity and efficiency of clinical trials.
• Existing methods often assume proportional hazards and do not fully address complexities like time-dependent losses or non-compliance.
• Comparing multiple (kappa >= 2) survival distributions presents unique statistical challenges.

Purpose of the Study:

• To present a generalized sample size formula for comparing kappa survival distributions.
• To extend existing sample size derivations to accommodate non-proportional hazards, time-dependent losses, non-compliance, and drop-in.
• To provide a formula for the stratified logrank test and demonstrate its utility in complex multi-arm trials.

Main Methods:

• The study derives a sample size formula based on the Tarone-Ware class of test statistics.
• The method extends Lakatos's derivation for comparing two survival distributions.
• A specific formula for the stratified logrank test is also developed.

Main Results:

• A novel sample size formula is presented for testing the equality of two or more survival distributions under complex conditions.
• The derived formulae are applicable to scenarios with non-proportional hazards, time-dependent losses, non-compliance, and drop-in.
• The paper offers practical guidance for utilizing these formulae in sample size calculations and power assessments for multi-arm clinical trials.

Conclusions:

• The proposed generalized sample size formulae enhance the design of clinical trials by accommodating realistic complexities.
• These methods provide a more robust framework for sample size determination when comparing multiple survival distributions.
• The findings are valuable for researchers conducting complex, multi-arm clinical trials requiring precise sample size and power estimations.