Meaningful change definitions: sample size planning for experimental intervention research

Area of Science:

• Biostatistics
• Health Services Research
• Clinical Trials

Background:

• Accurate sample size calculation is crucial for robust experimental intervention testing.
• Specifying an appropriate effect size is a key, yet often challenging, component of sample size estimation.
• Existing methods for selecting a priori effect sizes (e.g., conventions, prior research) have limitations.

Purpose of the Study:

• To identify and discuss problems associated with current methods of selecting effect sizes for study planning.
• To propose a novel, practical method for intervention researchers to determine appropriate a priori effect sizes.
• To facilitate precise sample size determination for testing intervention effectiveness.

Main Methods:

• Critical review of existing literature on effect size selection for sample size planning.
• Development of a new method centered on defining a 'meaningful change' relevant to applied researchers.
• Provision of practical guidance and R functions for implementing the proposed method.

Main Results:

• Identified significant limitations in conventional approaches to a priori effect size selection.
• The proposed method offers a structured way to define effect sizes based on meaningful change.
• The accompanying R functions simplify the application of this method for researchers.

Conclusions:

• The presented method addresses key challenges in selecting effect sizes for intervention study planning.
• This approach empowers applied researchers to set meaningful targets and calculate appropriate sample sizes.
• Improved sample size estimation leads to more precise and powerful tests of intervention effectiveness.