On the repeated measures designs and sample sizes for randomized controlled trials.

Area of Science:

• Biostatistics
• Clinical Trial Design
• Longitudinal Data Analysis

Background:

• Generalized linear mixed-effects models (GLMMs) are effective for longitudinal data with subject heterogeneity.
• Traditional randomized controlled trials (RCTs) often use pre-post data analysis with covariates, posing sample size calculation challenges.

Purpose of the Study:

• To propose a novel repeated measures design and sample size calculation method integrated with GLMMs.
• To offer a more efficient analytical approach for longitudinal data in RCTs.

Main Methods:

• The proposed method combines GLMMs with a repeated measures design.
• Sample size calculations consider both the number of subjects and repeated measures per subject.
• Likelihood-based methods are used for handling missing data under the missing at random assumption.

Main Results:

• The new design effectively handles missing data, a common issue in longitudinal studies.
• The proposed approach can potentially reduce the overall sample size compared to standard pre-post designs.
• The methodology is demonstrated using real-world RCT data.

Conclusions:

• The integrated GLMM and repeated measures design offers a flexible and powerful tool for longitudinal data analysis.
• This approach enhances data handling for missing values and optimizes sample size requirements in clinical trials.
• The findings support the adoption of this advanced design for future RCTs.