On non-inferiority margin and statistical tests in active control trials

Area of Science:

• Clinical Trials
• Biostatistics
• Pharmaceutical Research

Background:

• Selecting appropriate non-inferiority margins is crucial for active control trials.
• International Conference on Harmonization (ICH) guidelines recommend margins ensuring superiority over placebo if non-inferiority to active control is claimed.
• Variability must be considered in margin selection for robust trial outcomes.

Purpose of the Study:

• To propose a statistically justified method for selecting non-inferiority margins in active control trials.
• To derive statistical tests for non-inferiority when the margin is an unknown parameter.
• To provide a practical approach for clinical trial design and analysis.

Main Methods:

• Development of a novel method for selecting non-inferiority margins based on ICH guidelines and statistical principles.
• Derivation of statistical tests for non-inferiority applicable when the margin is not pre-defined.
• Application of the proposed method to a cancer clinical trial example using time to disease progression as the endpoint.

Main Results:

• A statistically sound methodology for non-inferiority margin selection is presented.
• New statistical tests are derived for scenarios with unknown non-inferiority margins.
• The proposed method is demonstrated effectively using a real-world cancer trial example.

Conclusions:

• The proposed method offers a robust approach to selecting non-inferiority margins and statistical tests in active control trials.
• This methodology enhances the reliability of non-inferiority claims by ensuring a meaningful comparison against both active controls and placebos.
• The findings are applicable to various therapeutic areas, including oncology, to improve clinical trial design and interpretation.